© 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. 34745
    Prev
    Next
    INDEX
    Explanations

    references to historical figures or political events

    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
    +0.15
    0.6%
    377
    +0.14
    0.6%
    640
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.15
    0.26
    735
    +0.14
    0.09
    311
    +0.13
    -0.02
    Negative Logits
     Maker
    -0.85
    ancial
    -0.85
     Remastered
    -0.80
    âĸij
    -0.79
     Undead
    -0.76
     Inquisitor
    -0.75
     Dare
    -0.74
     Titanic
    -0.74
     Shroud
    -0.74
     Beir
    -0.74
    POSITIVE LOGITS
    olition
    1.25
    raham
    1.21
    riel
    1.16
    ortion
    1.14
    duction
    1.14
    stract
    1.13
    bey
    1.11
    omination
    1.09
    rupt
    1.07
    dullah
    1.07
    Activations Density 6.726%

    No Known Activations