© 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. 2788
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to organizations or individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to machine learning

    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
    liest
    -0.72
    forcing
    -0.71
    patrick
    -0.69
    mins
    -0.67
    lies
    -0.63
    lishes
    -0.63
     Rear
    -0.63
    lain
    -0.62
    lished
    -0.61
    mit
    -0.60
    POSITIVE LOGITS
    anguage
    0.84
    yrics
    0.80
    DN
    0.79
    ounge
    0.79
    MX
    0.77
    aughter
    0.77
    iquid
    0.76
    endon
    0.76
    avery
    0.75
    TON
    0.75
    Activations Density 0.033%

    No Known Activations