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. 9-RES-JB
    6. 4354
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations or names, particularly related to a high school in South High School and various individuals with names like Middletown

    oai_token-act-pair · gpt-3.5-turbo

    names of people, places, or teams, particularly those starting with the letter 'M'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CBI
    -0.69
     Firm
    -0.59
     Crescent
    -0.55
     prism
    -0.54
     counsel
    -0.54
     lodging
    -0.54
    ECTION
    -0.54
     satellite
    -0.53
     [*]
    -0.53
     NRS
    -0.52
    POSITIVE LOGITS
    waukee
    0.94
    arella
    0.91
    emonic
    0.90
    intosh
    0.90
    nesota
    0.88
    gage
    0.86
    ICAN
    0.81
    achusetts
    0.81
    udi
    0.80
    hattan
    0.78
    Activations Density 0.137%

    No Known Activations