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 49152
    5. 8-RES_FS49152-JB
    6. 24023
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "old" in relation to various subjects

    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
    408
    +0.10
    0.5%
    735
    +0.09
    0.4%
    21
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.10
    0.02
    161
    +0.09
    0.02
    507
    +0.09
    0.02
    Negative Logits
    utterstock
    -0.92
    ï¸ı
    -0.85
     ILCS
    -0.84
    inventoryQuantity
    -0.80
    amera
    -0.80
    ommod
    -0.79
    gur
    -0.78
    omever
    -0.77
    illation
    -0.76
    pard
    -0.73
    POSITIVE LOGITS
     fashioned
    1.33
     timers
    0.96
    est
    0.96
     standby
    0.93
    fashioned
    0.79
     school
    0.79
     stomp
    0.78
     guard
    0.78
    school
    0.77
     regime
    0.77
    Activations Density 0.016%

    No Known Activations