© 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. 3336
    Prev
    Next
    INDEX
    Explanations

    trademarks and brand names

    oai_token-act-pair · gpt-3.5-turbo

    trademark symbols and related branding elements

    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
    ebin
    -0.76
    amus
    -0.75
    oids
    -0.69
    otta
    -0.67
    acle
    -0.66
    ias
    -0.65
    esses
    -0.64
    seless
    -0.64
     bleed
    -0.62
    enko
    -0.62
    POSITIVE LOGITS
    ternity
    0.65
    ãĤº
    0.65
    ©
    0.65
     Interactive
    0.64
    Wide
    0.64
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.62
     Organisation
    0.62
    ï¸ı
    0.60
    s
    0.59
     Creator
    0.59
    Activations Density 0.049%

    No Known Activations