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. 7-RES-JB
    6. 13001
    Prev
    Next
    INDEX
    Explanations

    mentions of legal matters or court-related terms like lawsuits or legal actions

    oai_token-act-pair · gpt-3.5-turbo

    references to a person named "Lud" or variations of that name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Painter
    -0.68
    #$
    -0.66
    borough
    -0.65
    ippi
    -0.57
    Constructed
    -0.57
    place
    -0.57
    terday
    -0.56
    Ͻ
    -0.56
    xon
    -0.55
     Slaughter
    -0.55
    POSITIVE LOGITS
    geon
    1.57
    geoning
    1.43
    apest
    1.26
    imentary
    1.18
    geons
    1.16
    iamond
    1.09
    ges
    1.05
    elta
    1.03
    gew
    1.01
    gie
    0.96
    Activations Density 0.023%

    No Known Activations