© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 16602
    Prev
    Next
    INDEX
    Explanations

    mentions of accomplishments or achievements

    oai_token-act-pair · gpt-3.5-turbo

    references to overall assessment or 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
    ody
    -0.81
     Lav
    -0.78
     Cinnamon
    -0.77
    akov
    -0.76
     cov
    -0.74
    DERR
    -0.74
     Ballard
    -0.70
     Dove
    -0.70
     Vag
    -0.68
     VID
    -0.68
    POSITIVE LOGITS
    9
    1.21
     9
    1.13
    09
    1.03
     Nine
    0.99
    Nine
    0.97
    nine
    0.95
     09
    0.92
    909
    0.90
     nine
    0.87
    99
    0.85
    Activations Density 0.185%

    No Known Activations