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. 46056
    Prev
    Next
    INDEX
    Explanations

    references to counterfeit products and their associated risks

    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
    641
    +0.15
    0.7%
    688
    +0.14
    0.6%
    624
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    688
    +0.15
    0.01
    641
    +0.14
    0.01
    103
    +0.12
    0.01
    Negative Logits
     GEAR
    -0.77
    nas
    -0.75
    DOWN
    -0.67
     ANGEL
    -0.67
    nah
    -0.64
     Narr
    -0.64
     Abram
    -0.64
    pheus
    -0.64
    worthy
    -0.61
     AFL
    -0.61
    POSITIVE LOGITS
    eling
    1.36
    els
    1.03
    lda
    1.03
    ck
    1.01
    elin
    0.92
    efe
    0.92
    ffer
    0.90
    cker
    0.90
    hler
    0.89
    lder
    0.89
    Activations Density 0.005%

    No Known Activations