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 24576
    5. 8-RES_FS24576-JB
    6. 21755
    Prev
    Next
    INDEX
    Explanations

    technical specifications and product details

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    +0.11
    0.5%
    127
    +0.10
    0.5%
    304
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    462
    +0.11
    0.04
    127
    +0.10
    0.03
    260
    +0.10
    0.04
    Negative Logits
    ADRA
    -0.66
    ryce
    -0.66
     Conversation
    -0.65
     Masquerade
    -0.64
    querque
    -0.63
    ¶æ
    -0.60
     possession
    -0.58
    iannopoulos
    -0.58
    ħĭ
    -0.57
    vertisement
    -0.56
    POSITIVE LOGITS
    576
    0.86
    arching
    0.76
    11
    0.68
    bringer
    0.67
    dogs
    0.65
    woods
    0.65
    pack
    0.64
    10
    0.64
    erences
    0.64
    000
    0.64
    Activations Density 0.153%

    No Known Activations