© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 33875
    Prev
    Next
    INDEX
    Explanations

    text related to physical traits and attributes related to strength and bodybuilding

    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
    67
    +0.15
    0.7%
    211
    +0.15
    0.7%
    537
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    68
    +0.15
    0.10
    23
    +0.15
    0.14
    154
    +0.11
    0.16
    Negative Logits
     CLSID
    -0.87
    esan
    -0.74
    elf
    -0.73
    smanship
    -0.71
     Estate
    -0.71
     Butterfly
    -0.70
    nesota
    -0.70
    ãģ®éŃĶ
    -0.70
    ãģ¦
    -0.70
     Pixie
    -0.69
    POSITIVE LOGITS
    wark
    1.35
    leted
    1.05
    usha
    0.91
     nerv
    0.89
    bul
    0.88
    rill
    0.87
    acan
    0.87
    ging
    0.86
    rush
    0.85
    bors
    0.83
    Activations Density 8.252%

    No Known Activations