© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 1342
    Prev
    Next
    INDEX
    Explanations

    phrases related to denial, ignorance, and illusion

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    756
    +0.15
    0.7%
    762
    +0.12
    0.5%
    255
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.15
    -0.02
    762
    +0.12
    0.09
    535
    +0.10
    0.04
    Negative Logits
    Alert
    -0.89
    Veter
    -0.86
     fundra
    -0.85
    ovember
    -0.81
     Veteran
    -0.78
    osponsors
    -0.76
    CDC
    -0.76
    tips
    -0.74
     ransomware
    -0.74
    akedown
    -0.73
    POSITIVE LOGITS
     atoms
    1.16
     immutable
    1.14
     beings
    1.13
     consciousness
    1.13
     finite
    1.12
     cosmos
    1.12
     emptiness
    1.07
    teness
    1.07
     ont
    1.05
     sentient
    1.04
    Activations Density 1.225%

    No Known Activations