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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 19951
    Prev
    Next
    INDEX
    Explanations

    social issues and community initiatives relating to support and assistance for marginalized groups

    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
    86
    +0.12
    0.5%
    508
    +0.10
    0.4%
    575
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    508
    +0.12
    0.05
    575
    +0.10
    0.06
    51
    +0.10
    0.04
    Negative Logits
     pse
    -0.93
    */(
    -0.86
     spoilers
    -0.81
     brute
    -0.80
     conjecture
    -0.78
    pload
    -0.77
     spoiler
    -0.75
     Conspiracy
    -0.75
     hairs
    -0.74
     speculation
    -0.73
    POSITIVE LOGITS
     homeless
    1.27
     Homeless
    1.26
     outreach
    1.21
     Volunteers
    1.16
     needy
    1.15
     homelessness
    1.13
     volunte
    1.12
     vocational
    1.12
     resettlement
    1.11
     wellness
    1.10
    Activations Density 0.633%

    No Known Activations