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. 41448
    Prev
    Next
    INDEX
    Explanations

    terms related to anatomy and archeology

    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
    99
    +0.12
    0.6%
    481
    +0.12
    0.5%
    622
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.02
    99
    +0.12
    0.01
    326
    +0.10
    0.01
    Negative Logits
    pour
    -0.95
    naire
    -0.93
    spr
    -0.92
    nered
    -0.92
    fw
    -0.86
    edin
    -0.83
    geon
    -0.83
    itsch
    -0.83
    ship
    -0.82
    ging
    -0.81
    POSITIVE LOGITS
     muscle
    0.88
     outline
    0.87
     skeletal
    0.87
     residue
    0.79
     limbs
    0.77
     likeness
    0.76
     fibers
    0.76
     woodland
    0.74
     splend
    0.73
     remnant
    0.72
    Activations Density 0.017%

    No Known Activations