© 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. 39933
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or political controversies

    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
    87
    +0.35
    3.1%
    64
    +0.21
    1.8%
    464
    +0.12
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    138
    +0.35
    0.46
    447
    +0.21
    0.47
    64
    +0.12
    -0.08
    Negative Logits
    iple
    -0.30
    arij
    -0.29
     Canaver
    -0.29
     âĢº
    -0.28
     aback
    -0.28
     Deadline
    -0.25
     puzzled
    -0.25
     spoilers
    -0.25
     Explan
    -0.25
     Kejriwal
    -0.25
    POSITIVE LOGITS
    )).
    0.70
    .).
    0.58
    ).
    0.53
    %).
    0.53
    ]).
    0.52
    ?).
    0.52
    )."
    0.51
    }.
    0.50
    ]."
    0.50
    ).[
    0.48
    Activations Density 2.387%

    No Known Activations