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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9041
    Prev
    Next
    INDEX
    Explanations

    references to journalistic articles and related commentary

    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
    373
    +0.19
    0.9%
    481
    +0.14
    0.7%
    314
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    680
    +0.19
    0.04
    362
    +0.14
    0.06
    572
    +0.10
    0.05
    Negative Logits
    BILITIES
    -0.61
    amina
    -0.60
     biologically
    -0.58
    Care
    -0.58
     footprint
    -0.57
    forces
    -0.57
     imposes
    -0.56
     economically
    -0.55
     athlet
    -0.55
     safely
    -0.54
    POSITIVE LOGITS
     titled
    0.84
     editor
    0.82
     blog
    0.82
    published
    0.78
     pdf
    0.78
    itled
    0.77
    NPR
    0.76
     commenter
    0.75
     journal
    0.74
     publication
    0.74
    Activations Density 0.824%

    No Known Activations