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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 37206
    Prev
    Next
    INDEX
    Explanations

    elements related to images, such as image tags and sources

    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
    644
    +0.12
    0.5%
    36
    +0.10
    0.5%
    123
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    315
    +0.12
    0.01
    289
    +0.10
    0.00
    496
    +0.09
    0.01
    Negative Logits
    etheless
    -0.88
     Permanent
    -0.77
    theless
    -0.76
    ese
    -0.75
    kamp
    -0.70
    ebus
    -0.70
    rase
    -0.70
    soType
    -0.66
    terday
    -0.65
     911
    -0.63
    POSITIVE LOGITS
    thumbnails
    0.95
    img
    0.93
    Upload
    0.89
     Thumbnails
    0.84
    wcsstore
    0.83
    Thumbnail
    0.80
    proc
    0.80
     img
    0.80
    ãĤ¨ãĥ«
    0.80
    adr
    0.79
    Activations Density 0.006%

    No Known Activations