© 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. 9-RES-JB
    11. 4557
    Prev
    Next
    INDEX
    Explanations

    words related to specific elements or features within a given context

    oai_token-act-pair · gpt-3.5-turbo

    noteworthily critical elements related to cultural phenomena and societal commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GOODMAN
    -0.87
    Effective
    -0.77
    erenn
    -0.74
    forth
    -0.73
     effective
    -0.72
     securely
    -0.72
    orthy
    -0.71
     lawfully
    -0.70
    avering
    -0.67
     sufficient
    -0.67
    POSITIVE LOGITS
     conco
    1.01
     stunts
    1.00
     noises
    0.95
     sculptures
    0.85
     trivia
    0.83
     antics
    0.83
     quirks
    0.83
     gimmick
    0.82
     tale
    0.82
    stros
    0.81
    Activations Density 0.624%

    No Known Activations