© 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. 34983
    Prev
    Next
    INDEX
    Explanations

    JavaScript code snippets

    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
    +0.16
    0.7%
    558
    +0.10
    0.5%
    604
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.16
    0.06
    604
    +0.10
    0.05
    100
    +0.09
    0.06
    Negative Logits
    udos
    -0.73
    ega
    -0.73
    conom
    -0.67
    hub
    -0.67
    olk
    -0.66
    entimes
    -0.66
    iday
    -0.65
    CBC
    -0.64
    ivan
    -0.64
    oya
    -0.64
    POSITIVE LOGITS
     EntityItem
    0.77
     Nex
    0.75
    ooters
    0.75
    ··
    0.74
     Baal
    0.69
     Diablo
    0.66
     comma
    0.66
     lambda
    0.62
    :{
    0.61
     Valhalla
    0.61
    Activations Density 7.977%

    No Known Activations