© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 39633
    Prev
    Next
    INDEX
    Explanations

    body parts, particularly focusing on feet

    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
    216
    +0.10
    0.5%
    372
    +0.09
    0.5%
    526
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.14
    372
    +0.09
    0.06
    0
    +0.09
    0.07
    Negative Logits
     Kore
    -0.69
     Shed
    -0.67
    NEWS
    -0.62
     Tone
    -0.61
     unfocusedRange
    -0.60
     Panther
    -0.59
     Mage
    -0.59
    ãĥ¼ãĥĨãĤ£
    -0.59
     Equality
    -0.59
    sson
    -0.56
    POSITIVE LOGITS
    isting
    0.85
    oped
    0.79
    etimes
    0.78
    vable
    0.77
    vel
    0.75
    isted
    0.74
    ips
    0.72
    uers
    0.71
    zzle
    0.70
    ecycle
    0.70
    Activations Density 3.645%

    No Known Activations