© 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. 12778
    Prev
    Next
    INDEX
    Explanations

    information related to political discussions and controversies

    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
    431
    +0.12
    0.5%
    506
    +0.11
    0.5%
    173
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    195
    +0.12
    0.02
    431
    +0.11
    0.05
    642
    +0.10
    0.03
    Negative Logits
    ahime
    -0.81
    gart
    -0.79
     hemor
    -0.78
    ascript
    -0.78
    ttes
    -0.78
    zie
    -0.75
    senal
    -0.74
    abad
    -0.73
     nomine
    -0.73
    sha
    -0.70
    POSITIVE LOGITS
    SPONSORED
    1.08
     happening
    0.83
    pires
    0.75
    IFF
    0.73
     variance
    0.73
    Magikarp
    0.72
    hest
    0.71
     Happ
    0.69
    lihood
    0.68
    Pixel
    0.67
    Activations Density 0.897%

    No Known Activations