© 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. 33980
    Prev
    Next
    INDEX
    Explanations

    references to the chronological order of events or stories

    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
    651
    +0.09
    0.5%
    447
    +0.09
    0.5%
    421
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    721
    +0.09
    0.10
    546
    +0.09
    0.10
    678
    +0.08
    0.09
    Negative Logits
    hammad
    -0.62
    Magikarp
    -0.60
    luent
    -0.58
    unta
    -0.57
    UGE
    -0.56
    holders
    -0.55
    yip
    -0.55
    urtles
    -0.55
     Shed
    -0.55
    umar
    -0.54
    POSITIVE LOGITS
     chron
    0.92
    iton
    0.91
    icity
    0.89
    ograph
    0.87
    ologically
    0.81
    icles
    0.81
    grain
    0.80
    ographs
    0.80
     Chron
    0.80
    icle
    0.80
    Activations Density 9.233%

    No Known Activations