© 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. 14179
    Prev
    Next
    INDEX
    Explanations

    specific patterns or tokens within the text that might be related to coding or markup language syntax

    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
    649
    +0.15
    0.6%
    343
    +0.13
    0.5%
    48
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.15
    0.14
    48
    +0.13
    0.11
    232
    +0.13
    0.10
    Negative Logits
     exha
    -1.04
    senal
    -0.98
     eleph
    -0.98
     obser
    -0.91
     gobl
    -0.90
    ¥ŀ
    -0.84
    phasis
    -0.84
    vation
    -0.84
     conflic
    -0.83
     unnecess
    -0.81
    POSITIVE LOGITS
    erman
    1.49
    es
    1.42
    enger
    1.35
    enzie
    1.25
    ert
    1.17
    ery
    1.16
    etts
    1.16
    esian
    1.13
    ian
    1.12
    ages
    1.12
    Activations Density 2.984%

    No Known Activations