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 49152
    5. 8-RES_FS49152-JB
    6. 43170
    Prev
    Next
    INDEX
    Explanations

    phrases related to enforcement or restrictions on behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    262
    +0.11
    0.5%
    125
    +0.11
    0.5%
    337
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    181
    +0.11
    0.01
    262
    +0.11
    0.01
    125
    +0.10
    0.01
    Negative Logits
     Primordial
    -0.64
    tein
    -0.63
    æµ
    -0.62
    jac
    -0.59
     Runes
    -0.58
     merged
    -0.58
     rise
    -0.57
    archives
    -0.56
    kefeller
    -0.56
     Oval
    -0.56
    POSITIVE LOGITS
    baugh
    0.88
     against
    0.87
    river
    0.82
    grading
    0.81
    graded
    0.79
    upon
    0.78
    ont
    0.76
     harshly
    0.75
     upon
    0.75
     forcefully
    0.75
    Activations Density 0.018%

    No Known Activations