© 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. 14038
    Prev
    Next
    INDEX
    Explanations

    SQL statements related to checking and access control

    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
    509
    +0.19
    0.6%
    640
    +0.17
    0.6%
    570
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    396
    +0.19
    0.04
    632
    +0.17
    0.04
    176
    +0.17
    0.04
    Negative Logits
     nucleus
    -1.04
    VIDIA
    -1.03
    owship
    -0.93
     undermin
    -0.92
     friendship
    -0.92
    raviolet
    -0.92
     necks
    -0.89
     hereditary
    -0.88
     bribes
    -0.86
     disadvant
    -0.85
    POSITIVE LOGITS
    else
    1.36
     [/
    1.29
     ACTIONS
    1.22
     EVENTS
    1.11
    endif
    1.09
     Finally
    1.09
    END
    1.07
     </
    1.06
    DATA
    1.06
    ########
    1.05
    Activations Density 0.344%

    No Known Activations