© 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. 16628
    Prev
    Next
    INDEX
    Explanations

    mentions of specific organizations or substances

    oai_token-act-pair · gpt-3.5-turbo

    specific terms and names related to geopolitical issues, military groups, and scientific concepts

    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
     VID
    -0.73
    ahime
    -0.66
    falls
    -0.64
    eah
    -0.63
    href
    -0.63
     Kers
    -0.62
    age
    -0.62
    Wilson
    -0.62
     Kear
    -0.60
    rising
    -0.59
    POSITIVE LOGITS
    ®,
    0.82
    Saharan
    0.76
    ®
    0.75
    âĦ¢
    0.72
    èĢħ
    0.70
    roid
    0.68
    xual
    0.65
    ervative
    0.64
    acher
    0.64
    tein
    0.63
    Activations Density 0.294%

    No Known Activations