© 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. 40408
    Prev
    Next
    INDEX
    Explanations

    words related to influential or significant individuals or figures

    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
    +0.23
    1.3%
    686
    +0.09
    0.5%
    554
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    197
    +0.23
    0.09
    596
    +0.09
    0.08
    216
    +0.09
    0.09
    Negative Logits
    ©¶æ
    -0.65
     faint
    -0.60
     boredom
    -0.57
     atoms
    -0.57
     flights
    -0.56
     bliss
    -0.55
     sickness
    -0.54
    ancies
    -0.54
     plane
    -0.54
    nance
    -0.53
    POSITIVE LOGITS
    street
    0.66
     shaping
    0.65
    cci
    0.64
    ablishment
    0.63
    代
    0.62
    TAIN
    0.61
    stone
    0.61
     Leading
    0.59
    ãĥķãĤ©
    0.58
    oux
    0.57
    Activations Density 12.014%

    No Known Activations