© 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. 3669
    Prev
    Next
    INDEX
    Explanations

    years specified in documents

    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
    +0.24
    1.1%
    497
    +0.13
    0.6%
    251
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    512
    +0.24
    0.07
    306
    +0.13
    0.09
    132
    +0.10
    0.07
    Negative Logits
    heet
    -0.84
    phy
    -0.82
    anooga
    -0.81
    itionally
    -0.81
    imore
    -0.81
    ï¸
    -0.81
    avascript
    -0.77
    ournals
    -0.76
    itional
    -0.75
    ipation
    -0.75
    POSITIVE LOGITS
    å¹
    0.84
    nd
    0.81
     onwards
    0.77
     Reincarn
    0.74
    20439
    0.68
     Budget
    0.67
    BUS
    0.67
    ãģ®éŃĶ
    0.65
     onward
    0.64
     Tigers
    0.64
    Activations Density 4.813%

    No Known Activations