© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 1757
    Prev
    Next
    INDEX
    Explanations

    proper nouns used as identifiers or names

    oai_token-act-pair · gpt-3.5-turbo

    instances where individuals or entities are identified

    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
    orld
    -0.83
    eries
    -0.73
    imeo
    -0.73
    gard
    -0.72
    ework
    -0.70
    xp
    -0.70
    sei
    -0.69
    fare
    -0.67
    perty
    -0.66
    emate
    -0.66
    POSITIVE LOGITS
     identification
    0.75
     è£ıè
    0.74
     Identification
    0.74
     markings
    0.73
     identifiers
    0.73
    rified
    0.73
    %%
    0.71
    PsyNetMessage
    0.70
     surn
    0.70
     discrepancies
    0.70
    Activations Density 0.022%

    No Known Activations