© 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. 18931
    Prev
    Next
    INDEX
    Explanations

    links or references indicated by specific formatting, like Ċ

    oai_token-act-pair · gpt-3.5-turbo

    indicators of digital engagement and social media presence

    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
    etheless
    -0.72
     proport
    -0.68
     tremend
    -0.65
     practition
    -0.64
     exting
    -0.63
     thous
    -0.62
     representation
    -0.62
     ageing
    -0.60
     citiz
    -0.60
     satell
    -0.60
    POSITIVE LOGITS
    Featured
    0.93
    <|endoftext|>
    0.92
    UPDATE
    0.90
    Advertisements
    0.84
    Follow
    0.84
    Correction
    0.83
    SOURCE
    0.82
    Tomorrow
    0.80
    Posted
    0.80
    Thumbnail
    0.79
    Activations Density 0.309%

    No Known Activations