Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 24182
    Prev
    Next
    INDEX
    Explanations

    references to celebrities or famous individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to stars or prominent figures

    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
    odcast
    -0.80
    Downloadha
    -0.71
    iHUD
    -0.69
     LIA
    -0.68
    »Ĵ
    -0.64
     Schne
    -0.64
    channelAvailability
    -0.63
     Forth
    -0.62
    ython
    -0.61
    ipop
    -0.59
    POSITIVE LOGITS
    bucks
    1.20
    burst
    1.17
    let
    1.08
    stru
    1.04
    lets
    1.03
    rer
    1.02
    ry
    1.00
    vation
    1.00
    light
    1.00
    fish
    0.98
    Activations Density 0.032%

    No Known Activations