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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 1536
    5. 8-RES_FS1536-JB
    6. 829
    Prev
    Next
    INDEX
    Explanations

    names of individuals who are mentioned in the text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    430
    +0.19
    0.9%
    232
    +0.12
    0.5%
    408
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.19
    0.10
    232
    +0.12
    0.08
    699
    +0.10
    0.06
    Negative Logits
     appre
    -0.85
     actionGroup
    -0.81
     destro
    -0.74
     wheelchair
    -0.71
     tremend
    -0.66
    pmwiki
    -0.66
    orph
    -0.66
    rawdownloadcloneembedreportprint
    -0.65
     unden
    -0.65
    phia
    -0.64
    POSITIVE LOGITS
     Hyde
    0.89
     Claus
    0.84
     Hussein
    0.81
     Farage
    0.81
     Freeze
    0.80
     Obama
    0.80
     Ack
    0.77
     Universe
    0.77
     Justice
    0.76
     Putin
    0.76
    Activations Density 0.729%

    No Known Activations