© 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. 7536
    Prev
    Next
    INDEX
    Explanations

    issues or challenges in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    statements that identify or describe problems

    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
    riel
    -0.85
    avored
    -0.83
    Happy
    -0.74
     cheers
    -0.74
    augh
    -0.73
    oward
    -0.72
     praises
    -0.72
    erville
    -0.71
    avor
    -0.71
    azel
    -0.70
    POSITIVE LOGITS
     compounded
    0.97
     inability
    0.96
     finding
    0.95
     endemic
    0.93
     inconsistency
    0.92
     figuring
    0.90
     exacerbated
    0.90
     misunderstanding
    0.87
     preventing
    0.87
     lack
    0.86
    Activations Density 0.204%

    No Known Activations