© 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. 8905
    Prev
    Next
    INDEX
    Explanations

    information related to security breaches and ransom incidents

    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
    545
    +0.14
    0.6%
    409
    +0.11
    0.5%
    133
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    409
    +0.14
    0.03
    133
    +0.11
    0.03
    545
    +0.09
    0.02
    Negative Logits
    wikipedia
    -0.91
     Ambro
    -0.84
    ãĥķãĤ©
    -0.81
     Pru
    -0.80
     Orn
    -0.76
     ISIL
    -0.73
    çļ
    -0.72
    ORN
    -0.72
    brid
    -0.71
     Rosen
    -0.70
    POSITIVE LOGITS
     week
    1.41
     day
    1.34
     month
    1.30
     Month
    1.27
     days
    1.26
     Days
    1.25
     Week
    1.25
     Day
    1.23
    day
    1.19
     DAY
    1.18
    Activations Density 0.113%

    No Known Activations