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. 23882
    Prev
    Next
    INDEX
    Explanations

    phrases related to work and efforts being made or needed

    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
    524
    +0.10
    0.5%
    670
    +0.10
    0.4%
    58
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    458
    +0.10
    0.02
    540
    +0.10
    0.03
    531
    +0.10
    0.02
    Negative Logits
    threat
    -0.69
     stormed
    -0.68
     derog
    -0.66
    majority
    -0.66
     cursed
    -0.65
    cemic
    -0.64
    het
    -0.63
    ethy
    -0.63
    tall
    -0.61
     Warning
    -0.60
    POSITIVE LOGITS
     done
    1.10
     undertaken
    1.10
     underway
    0.99
     expended
    0.97
    done
    0.89
     performed
    0.85
     undone
    0.83
    umen
    0.81
     PROG
    0.80
     groundwork
    0.80
    Activations Density 0.135%

    No Known Activations