© 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. 3642
    Prev
    Next
    INDEX
    Explanations

    names containing the specific sequence "Kem"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly their names

    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
    ODUCT
    -0.70
    velength
    -0.69
    ACTED
    -0.68
     Aires
    -0.67
    udence
    -0.65
    terday
    -0.64
    ACT
    -0.64
    externalActionCode
    -0.63
    BILITY
    -0.61
    azines
    -0.60
    POSITIVE LOGITS
    erer
    0.88
    eters
    0.87
    ety
    0.85
    mares
    0.83
    enstein
    0.81
    ulations
    0.79
    lock
    0.79
    enburg
    0.78
    hammer
    0.78
    untu
    0.78
    Activations Density 0.018%

    No Known Activations