© 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. 32920
    Prev
    Next
    INDEX
    Explanations

    city names and specific locations

    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
    548
    +0.04
    0.5%
    535
    +0.04
    0.5%
    489
    +0.04
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.04
    0.13
    284
    +0.04
    0.12
    616
    +0.04
    0.10
    Negative Logits
     laun
    -0.28
    ktop
    -0.26
    ÄŁ
    -0.26
     Lauder
    -0.26
     Zimmer
    -0.26
    lder
    -0.24
    etter
    -0.23
     Fernand
    -0.23
    )].
    -0.22
     dove
    -0.22
    POSITIVE LOGITS
    ĻĤ
    0.30
    itudes
    0.28
    Pause
    0.28
    ilateral
    0.27
    ²¾
    0.27
    pret
    0.26
    acle
    0.25
    itionally
    0.25
    parse
    0.24
    iculture
    0.24
    Activations Density 14.178%

    No Known Activations