© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 45863
    Prev
    Next
    INDEX
    Explanations

    numerical sequences and technical details like track numbers and file information

    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
    +0.33
    1.5%
    640
    +0.29
    1.4%
    481
    +0.19
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.33
    0.29
    6
    +0.29
    0.22
    430
    +0.19
    0.21
    Negative Logits
     exploited
    -0.80
     behavi
    -0.76
     advis
    -0.74
     bonded
    -0.72
     rall
    -0.72
     underestimated
    -0.71
     disrupted
    -0.68
     withd
    -0.68
    oling
    -0.67
     heroine
    -0.67
    POSITIVE LOGITS
    jar
    1.05
    sbm
    1.03
    htm
    1.02
    icio
    0.93
    jpg
    0.92
    debian
    0.91
    exe
    0.86
    zip
    0.85
    66666666
    0.84
    txt
    0.84
    Activations Density 8.857%

    No Known Activations