© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 3736
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific individual named Bennett

    oai_token-act-pair · gpt-3.5-turbo

    the name "Bennett" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ACTED
    -0.76
    ctions
    -0.74
    DonaldTrump
    -0.73
    ural
    -0.70
     extrem
    -0.68
    lycer
    -0.68
    ources
    -0.67
    ocrine
    -0.67
    Iraq
    -0.67
    sis
    -0.66
    POSITIVE LOGITS
     Bennett
    0.97
    ucket
    0.87
    ennett
    0.86
    wana
    0.82
    stown
    0.82
    igham
    0.82
    jee
    0.81
     Sheldon
    0.79
     Bros
    0.78
    theless
    0.76
    Activations Density 0.010%

    No Known Activations