© 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. 1396
    Prev
    Next
    INDEX
    Explanations

    written inscriptions, readings, and documentation

    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
    679
    +0.18
    0.8%
    430
    +0.11
    0.5%
    547
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.18
    0.12
    274
    +0.11
    0.09
    70
    +0.10
    0.07
    Negative Logits
    estern
    -0.86
    phant
    -0.80
     volcano
    -0.73
     Peaks
    -0.73
    uncture
    -0.71
     mortal
    -0.70
    pter
    -0.70
     Dise
    -0.68
    castle
    -0.68
    ä½ľ
    -0.64
    POSITIVE LOGITS
     omin
    0.89
     goodbye
    0.81
    margin
    0.78
    dated
    0.76
     cris
    0.76
     quoting
    0.74
    ettings
    0.72
     '[
    0.70
     "(
    0.69
     nothing
    0.69
    Activations Density 1.681%

    No Known Activations