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. 724
    Prev
    Next
    INDEX
    Explanations

    personal opinions or reflections expressed in the text

    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
    430
    +0.10
    0.5%
    589
    +0.10
    0.4%
    19
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    105
    +0.10
    0.02
    19
    +0.10
    0.02
    279
    +0.10
    0.02
    Negative Logits
     Fors
    -0.61
     optionally
    -0.59
     yourselves
    -0.58
    perty
    -0.58
    roup
    -0.58
     TMZ
    -0.57
    batch
    -0.57
    Loading
    -0.55
    ombs
    -0.55
     Reuters
    -0.54
    POSITIVE LOGITS
     personally
    1.11
    Interstitial
    0.93
    adow
    0.86
    adows
    0.82
    é¾įå¥ij士
    0.80
    cca
    0.77
    ãĥĩãĤ£
    0.74
    ager
    0.72
    OGR
    0.70
    ©¶æ¥µ
    0.70
    Activations Density 0.036%

    No Known Activations