© 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. 14213
    Prev
    Next
    INDEX
    Explanations

    chemical compounds

    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
    +0.17
    0.9%
    288
    +0.11
    0.6%
    549
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    549
    +0.17
    0.07
    288
    +0.11
    0.20
    623
    +0.09
    0.04
    Negative Logits
    ipeg
    -0.69
    hips
    -0.61
     Gunn
    -0.61
    hhhh
    -0.60
    corn
    -0.60
    ¿
    -0.60
    Ŀ
    -0.59
    abet
    -0.59
    */(
    -0.57
    encer
    -0.57
    POSITIVE LOGITS
    inct
    0.66
    alities
    0.65
     annex
    0.63
     compounds
    0.62
     compound
    0.61
    aque
    0.58
     fracture
    0.58
    iliary
    0.57
     cannabinoid
    0.56
    ities
    0.55
    Activations Density 9.343%

    No Known Activations