Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 1170
    Prev
    Next
    INDEX
    Explanations

    web addresses and related information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    107
    +0.10
    0.5%
    95
    +0.10
    0.5%
    331
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.10
    0.04
    409
    +0.10
    0.04
    586
    +0.09
    0.04
    Negative Logits
     Mach
    -0.64
     Koen
    -0.64
     guiActive
    -0.63
     Ribbon
    -0.62
     Kik
    -0.61
     Goo
    -0.61
     Outbreak
    -0.59
     msec
    -0.58
     Chun
    -0.58
     Rune
    -0.57
    POSITIVE LOGITS
    /)
    1.55
    _
    1.50
    _-_
    1.46
    _(
    1.37
    __
    1.30
    /?
    1.26
    /,
    1.19
    />
    1.16
    /#
    1.15
    _.
    1.11
    Activations Density 0.242%

    No Known Activations