© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 3-RES-JB
    11. 1550
    Prev
    Next
    INDEX
    Explanations

    words related to written documents or papers

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with "whiteness" and racial identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raltar
    -0.76
    VID
    -0.74
    orsi
    -0.72
    Reference
    -0.71
    aeda
    -0.71
    HAM
    -0.69
     GEAR
    -0.68
    Population
    -0.67
    ologne
    -0.67
    PsyNetMessage
    -0.67
    POSITIVE LOGITS
    ewater
    1.19
    ening
    1.01
     whit
    1.01
    elist
    1.00
    eness
    0.99
    ened
    0.93
    estone
    0.87
    bread
    0.86
    etooth
    0.84
    ety
    0.83
    Activations Density 0.006%

    No Known Activations