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

    Neuronpedia

    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. 6063
    Prev
    Next
    INDEX
    Explanations

    statements expressing opinions or beliefs

    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
    393
    +0.21
    0.8%
    92
    +0.12
    0.5%
    104
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    677
    +0.21
    0.06
    142
    +0.12
    0.06
    393
    +0.12
    0.07
    Negative Logits
    planes
    -1.00
    alties
    -1.00
    ngth
    -0.99
    anas
    -0.93
    staking
    -0.92
    dies
    -0.92
    ukemia
    -0.92
    chev
    -0.91
    oes
    -0.91
    aneers
    -0.90
    POSITIVE LOGITS
     blatant
    0.96
     chance
    0.90
     disrespectful
    0.85
     honorable
    0.83
     flawless
    0.82
     continuation
    0.82
     serious
    0.82
     exciting
    0.82
     spac
    0.81
    actly
    0.81
    Activations Density 0.772%

    No Known Activations