Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 34609
    Prev
    Next
    INDEX
    Explanations

    technical programming keywords and terms

    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
    •Layer 6 UMAP region: Mostly-local line at bottom - local

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.31
    3.3%
    64
    +0.10
    1.0%
    497
    +0.06
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    459
    +0.31
    0.25
    97
    +0.10
    0.08
    464
    +0.06
    0.14
    Negative Logits
    .).
    -0.50
    ]."
    -0.45
    }.
    -0.41
    )).
    -0.41
    ?).
    -0.40
    ]).
    -0.39
    !).
    -0.38
    ).
    -0.38
     accordingly
    -0.37
    ).[
    -0.36
    POSITIVE LOGITS
     divided
    0.22
    arij
    0.21
    ':
    0.21
     Huntington
    0.21
     Introduction
    0.21
     Bernstein
    0.20
     (%
    0.19
     HC
    0.19
    \":
    0.19
     underestimated
    0.19
    Activations Density 31.447%

    No Known Activations