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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13741
    Prev
    Next
    INDEX
    Explanations

    expressions of thoughts, feelings, and perceptions

    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
    647
    +0.10
    0.4%
    19
    +0.09
    0.4%
    185
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    638
    +0.10
    0.07
    271
    +0.09
    0.05
    259
    +0.09
    0.06
    Negative Logits
    idelines
    -0.83
     defic
    -0.75
    Notable
    -0.72
    license
    -0.67
    alpha
    -0.67
    eworks
    -0.67
     deviations
    -0.66
     pole
    -0.66
     poles
    -0.65
    ignore
    -0.65
    POSITIVE LOGITS
     seeing
    0.89
    Seeing
    0.88
     knowing
    0.80
     remembering
    0.78
     behold
    0.78
     humiliation
    0.77
     witnessing
    0.76
     agony
    0.76
     feeling
    0.75
     Sponge
    0.73
    Activations Density 4.060%

    No Known Activations