© 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. 8-RES-JB
    11. 3290
    Prev
    Next
    INDEX
    Explanations

    IDs and details of deceased individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to deceased individuals and related administrative or legal matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.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

    Negative Logits
    lopp
    -0.65
    tro
    -0.60
    pires
    -0.56
    poons
    -0.55
    FIG
    -0.55
    poon
    -0.55
    )?
    -0.54
    ?).
    -0.54
    vae
    -0.52
    awks
    -0.52
    POSITIVE LOGITS
     because
    0.80
     unless
    0.80
     until
    0.72
     while
    0.71
     via
    0.70
     whilst
    0.69
     Including
    0.68
     insofar
    0.65
     including
    0.64
     through
    0.63
    Activations Density 0.892%

    No Known Activations