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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 1670
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations, particularly those related to the West region

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    527
    +0.12
    0.5%
    624
    +0.11
    0.5%
    526
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.12
    0.06
    527
    +0.11
    0.04
    65
    +0.10
    0.05
    Negative Logits
    etsk
    -0.95
    staking
    -0.85
    cffff
    -0.79
    ptive
    -0.75
    Æ
    -0.75
    displayText
    -0.74
    acet
    -0.73
     confir
    -0.71
    Downloadha
    -0.71
    undo
    -0.71
    POSITIVE LOGITS
     Indies
    1.23
    minster
    1.19
     Coast
    1.18
    cott
    1.11
    lake
    1.08
     Midlands
    1.07
    phal
    1.01
    pac
    1.00
    chester
    0.99
     Wing
    0.99
    Activations Density 0.454%

    No Known Activations