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 49152
    5. 8-RES_FS49152-JB
    6. 26376
    Prev
    Next
    INDEX
    Explanations

    the presence of specific personal names or identifiers

    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
    481
    +0.19
    0.9%
    392
    +0.11
    0.5%
    165
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.19
    0.03
    392
    +0.11
    0.03
    659
    +0.10
    0.03
    Negative Logits
     Princ
    -0.96
     OM
    -0.87
     ple
    -0.80
     indo
    -0.79
     Um
    -0.75
     obser
    -0.73
     Pis
    -0.73
     Som
    -0.72
     Marian
    -0.72
    Ser
    -0.71
    POSITIVE LOGITS
    ck
    1.25
    cks
    1.25
    ock
    1.14
    ack
    1.12
    ocker
    1.04
    acks
    1.02
    ocks
    1.02
    rack
    0.98
    ucket
    0.98
    icken
    0.98
    Activations Density 0.068%

    No Known Activations