© 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. 3-RES-JB
    11. 24427
    Prev
    Next
    INDEX
    Explanations

    names, likely from a legal or political context

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific last names or surnames

    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
    agascar
    -0.74
    etheless
    -0.74
    rarily
    -0.72
    nesia
    -0.71
    uyomi
    -0.71
    ioned
    -0.69
    ahime
    -0.69
    dit
    -0.68
     facilit
    -0.66
    thro
    -0.66
    POSITIVE LOGITS
     Scha
    1.14
    efer
    1.00
    ven
    0.91
    uth
    0.88
     Osw
    0.84
    pling
    0.82
    uble
    0.82
    itz
    0.80
    adium
    0.80
    ivas
    0.79
    Activations Density 0.007%

    No Known Activations