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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11288
    Prev
    Next
    INDEX
    Explanations

    references to locations, political conversations, and technical product features

    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
    60
    +0.13
    0.6%
    211
    +0.13
    0.6%
    471
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    60
    +0.13
    0.03
    211
    +0.13
    0.02
    129
    +0.10
    0.02
    Negative Logits
    SHIP
    -0.69
     Moonlight
    -0.66
     AFL
    -0.65
    beans
    -0.62
     FTA
    -0.60
    soever
    -0.60
     Jinn
    -0.60
    doms
    -0.60
    OLOGY
    -0.59
     Emmanuel
    -0.59
    POSITIVE LOGITS
    ayed
    1.28
    phi
    1.21
    aware
    1.17
    usional
    1.17
    icate
    1.16
    ivered
    1.15
    ivery
    1.15
    ivering
    1.14
    inqu
    1.10
    iber
    1.09
    Activations Density 0.012%

    No Known Activations