© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 6000
    Prev
    Next
    INDEX
    Explanations

    terms related to business and finance entities

    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
    392
    +0.10
    0.4%
    21
    +0.09
    0.4%
    566
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.02
    487
    +0.09
    0.02
    392
    +0.09
    0.03
    Negative Logits
    rooms
    -0.74
     Brach
    -0.68
    ãĤª
    -0.67
    ãĤ©
    -0.66
    minster
    -0.66
    lets
    -0.66
    rouse
    -0.66
    inelli
    -0.65
    flies
    -0.64
    practice
    -0.64
    POSITIVE LOGITS
    PUT
    1.37
    OVA
    1.22
    FOR
    1.22
    TERN
    1.14
    OF
    1.13
    IST
    1.11
    OR
    1.10
    OX
    1.09
    BRE
    1.09
    ROR
    1.09
    Activations Density 0.054%

    No Known Activations