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 3072
    5. 8-RES_FS3072-JB
    6. 1894
    Prev
    Next
    INDEX
    Explanations

    phrases related to human rights issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    515
    +0.13
    0.6%
    332
    +0.13
    0.6%
    719
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    515
    +0.13
    0.06
    332
    +0.13
    0.06
    719
    +0.10
    0.05
    Negative Logits
    urations
    -0.69
    RET
    -0.68
    eryl
    -0.68
    forth
    -0.68
     Transcript
    -0.67
    kick
    -0.67
    href
    -0.66
    onne
    -0.65
    RAG
    -0.65
    creen
    -0.64
    POSITIVE LOGITS
     beings
    1.42
    itarian
    1.24
    itar
    1.19
    oids
    1.09
    itary
    0.99
    istic
    0.97
     embryonic
    0.96
     rights
    0.95
    zee
    0.94
    izing
    0.93
    Activations Density 0.378%

    No Known Activations