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. 16850
    Prev
    Next
    INDEX
    Explanations

    website-related prompts and calls to action

    oai_token-act-pair · gpt-3.5-turbo

    calls to action and references to privacy policies

    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
    ishable
    -0.60
     Fargo
    -0.56
     Morg
    -0.53
     tongues
    -0.52
    ugu
    -0.51
    canon
    -0.50
    omorphic
    -0.48
     Homer
    -0.48
    lished
    -0.48
     Valhalla
    -0.48
    POSITIVE LOGITS
    dinand
    0.62
    omever
    0.59
    ockets
    0.57
    orpor
    0.55
    orce
    0.55
     Agenda
    0.53
    eph
    0.52
    settings
    0.51
    ħĭ
    0.51
    aws
    0.50
    Activations Density 0.073%

    No Known Activations