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. 11-RES-JB
    6. 18975
    Prev
    Next
    INDEX
    Explanations

    mentions of public places and related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to public spaces and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Parameter
    -0.71
    argon
    -0.67
    igible
    -0.65
    amaz
    -0.63
    llan
    -0.62
     Tactics
    -0.62
    endish
    -0.59
    ogen
    -0.59
     Velocity
    -0.59
     Monstrous
    -0.59
    POSITIVE LOGITS
     restrooms
    1.20
     squares
    1.09
     bathrooms
    1.04
     spaces
    1.02
     toilets
    1.01
     restroom
    0.99
     baths
    0.97
     servants
    0.96
     transportation
    0.94
     places
    0.92
    Activations Density 0.039%

    No Known Activations