© 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 Local
    9. 6-RES_SCL-AJT
    11. 33161
    Prev
    Next
    INDEX
    Explanations

    general topics or overarching concepts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    302
    +0.14
    0.6%
    508
    +0.14
    0.5%
    459
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    555
    +0.14
    0.06
    508
    +0.14
    0.07
    302
    +0.13
    0.08
    Negative Logits
    ÄŁ
    -0.98
    ï¸
    -0.95
    bley
    -0.85
    lda
    -0.85
    rero
    -0.84
    zzi
    -0.84
    nown
    -0.83
    ILLE
    -0.83
    ZZ
    -0.82
    ħĭ
    -0.82
    POSITIVE LOGITS
    izations
    1.48
     relativity
    1.25
    isations
    1.25
    ization
    1.22
    ignment
    1.17
     aviation
    1.11
    wealth
    1.11
    izing
    1.10
    ised
    1.09
    izable
    1.07
    Activations Density 2.653%

    No Known Activations