© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 14505
    Prev
    Next
    INDEX
    Explanations

    technical specifications and details related to technology devices

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    +0.07
    0.5%
    674
    +0.07
    0.4%
    231
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    137
    +0.07
    0.01
    373
    +0.07
    -0.01
    326
    +0.07
    0.02
    Negative Logits
    eer
    -0.57
    eers
    -0.56
    heid
    -0.53
    resolution
    -0.50
     surrogate
    -0.49
    eering
    -0.48
     Kod
    -0.48
     phosphate
    -0.47
     Byrne
    -0.47
    cliffe
    -0.47
    POSITIVE LOGITS
    OPS
    0.60
    ï¸ı
    0.59
     Flavoring
    0.55
    IPP
    0.52
    TPS
    0.52
    anish
    0.50
    INGTON
    0.50
     Anonymous
    0.49
     UPDATE
    0.49
    :{
    0.49
    Activations Density 0.082%

    No Known Activations