© 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. 8521
    Prev
    Next
    INDEX
    Explanations

    words related to formal recognition or acknowledgment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to acknowledgment or validation of entities, concepts, or statuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ieri
    -0.82
    olit
    -0.78
    ework
    -0.72
    quin
    -0.69
    quer
    -0.69
    oys
    -0.68
    stead
    -0.68
    eware
    -0.67
    achus
    -0.67
    usterity
    -0.66
    POSITIVE LOGITS
    ibly
    0.89
    ledged
    0.88
    ibility
    0.75
     landmarks
    0.73
    ances
    0.71
     shortcomings
    0.69
    enance
    0.69
     Scotia
    0.68
     deficiencies
    0.67
    worthiness
    0.66
    Activations Density 0.046%

    No Known Activations