© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 12987
    Prev
    Next
    INDEX
    Explanations

    information related to journalism and news organizations, possibly with a focus on sustainability and accessibility

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    631
    +0.13
    0.5%
    503
    +0.12
    0.5%
    290
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.13
    0.06
    393
    +0.12
    0.05
    385
    +0.12
    0.04
    Negative Logits
    uphem
    -1.06
    apon
    -1.03
    ngth
    -0.96
    ortium
    -0.96
    emale
    -0.96
    wagen
    -0.88
    pec
    -0.85
    aughs
    -0.85
     weap
    -0.85
    akov
    -0.84
    POSITIVE LOGITS
     extent
    0.82
     domain
    0.81
     devastation
    0.79
     late
    0.75
     deficit
    0.74
     distribution
    0.73
     site
    0.73
     environment
    0.72
     Sierra
    0.72
     margins
    0.71
    Activations Density 0.349%

    No Known Activations