© 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. 34789
    Prev
    Next
    INDEX
    Explanations

    proper names of people and places

    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
    447
    +0.31
    1.5%
    481
    +0.10
    0.5%
    649
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    556
    +0.31
    0.11
    659
    +0.10
    0.11
    294
    +0.09
    0.01
    Negative Logits
     consolidation
    -0.67
    glers
    -0.62
     anat
    -0.59
    EStream
    -0.56
     readiness
    -0.55
    perty
    -0.54
    selection
    -0.54
     jelly
    -0.51
     psychiatrists
    -0.51
     conventions
    -0.51
    POSITIVE LOGITS
    arth
    0.76
    ahu
    0.76
    asons
    0.71
     Pradesh
    0.71
    ÄŁ
    0.66
    oji
    0.64
    ndra
    0.64
     Odin
    0.63
    rue
    0.63
    iev
    0.62
    Activations Density 20.045%

    No Known Activations