© 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. 10-RES-JB
    11. 18750
    Prev
    Next
    INDEX
    Explanations

    abbreviations with the format "E." followed by a single letter

    oai_token-act-pair · gpt-3.5-turbo

    punctuated sentences indicating significant moments or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     latitude
    -0.76
    wcs
    -0.74
    eele
    -0.71
     fixme
    -0.66
    hari
    -0.65
    ioned
    -0.65
     neutrality
    -0.63
    alysed
    -0.62
     comprom
    -0.62
    arios
    -0.62
    POSITIVE LOGITS
     coli
    1.39
    TERN
    0.90
     Cummings
    0.84
    mail
    0.82
     Coy
    0.76
    mails
    0.75
     Howard
    0.73
    Sah
    0.70
    sports
    0.68
    theless
    0.68
    Activations Density 0.021%

    No Known Activations