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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 1794
    Prev
    Next
    INDEX
    Explanations

    information related to various social issues and events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    303
    +0.10
    0.5%
    640
    +0.09
    0.4%
    632
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    303
    +0.10
    0.06
    335
    +0.09
    0.05
    632
    +0.09
    0.05
    Negative Logits
     advis
    -0.75
     stewards
    -0.66
     confidentiality
    -0.64
     chopping
    -0.64
    imus
    -0.61
    redients
    -0.61
     roam
    -0.60
     waterfall
    -0.59
    aults
    -0.58
    umers
    -0.57
    POSITIVE LOGITS
    E
    0.97
    Va
    0.95
    O
    0.91
    A
    0.90
    J
    0.87
    C
    0.87
    S
    0.84
    Skill
    0.83
    MX
    0.82
    AX
    0.81
    Activations Density 0.234%

    No Known Activations