© 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. 10-RES-JB
    11. 12073
    Prev
    Next
    INDEX
    Explanations

    instances where the text discusses a singular, specific item or topic among a set of choices

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etz
    -0.80
    storms
    -0.74
    des
    -0.73
    gnu
    -0.69
    redits
    -0.69
    illus
    -0.68
    invoke
    -0.68
    skirts
    -0.68
    mire
    -0.66
    ruary
    -0.66
    POSITIVE LOGITS
     thing
    1.36
     conceivable
    1.24
     reason
    1.24
     exception
    1.20
     way
    1.19
     remaining
    1.17
     viable
    1.13
     downside
    1.11
     sane
    1.10
     difference
    1.09
    Activations Density 0.051%

    No Known Activations