© 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 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. 3286
    Prev
    Next
    INDEX
    Explanations

    percentages or numerical values

    oai_token-act-pair · gpt-3.5-turbo
    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
    ndra
    -0.68
    anski
    -0.66
    bed
    -0.61
    fram
    -0.59
     dagger
    -0.59
     sed
    -0.59
    oak
    -0.59
     Hamm
    -0.59
     bait
    -0.58
    yang
    -0.57
    POSITIVE LOGITS
    9999
    1.19
    999
    1.16
    percent
    1.01
    99
    0.94
     percentile
    0.92
    ãĤ¼ãĤ¦ãĤ¹
    0.90
    998
    0.86
    98
    0.85
    %%%%
    0.84
    95
    0.83
    Activations Density 0.074%

    No Known Activations