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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3-RES-JB
    6. 2141
    Prev
    Next
    INDEX
    Explanations

    mentions of educational institutions, with a focus on Carnegie Mellon University

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific universities and notable individuals associated with them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wad
    -0.70
    urious
    -0.68
    bows
    -0.67
    cence
    -0.67
     Fry
    -0.65
     prick
    -0.62
    uably
    -0.62
    nec
    -0.62
    cé
    -0.62
    chini
    -0.62
    POSITIVE LOGITS
    holders
    0.94
    essage
    0.87
     holders
    0.84
    umbn
    0.82
    mson
    0.81
    aneers
    0.80
    oday
    0.80
    ĸļ
    0.79
    aternity
    0.77
    andr
    0.76
    Activations Density 0.021%

    No Known Activations