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. 11-RES-JB
    6. 2972
    Prev
    Next
    INDEX
    Explanations

    phrases related to local government or city council

    oai_token-act-pair · gpt-3.5-turbo

    references to council members and their activities

    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
    TPS
    -0.70
     Haram
    -0.69
    CRIPTION
    -0.68
    terson
    -0.66
    ionage
    -0.66
    èª
    -0.65
     Emerson
    -0.60
     JPM
    -0.60
    Downloadha
    -0.59
     goose
    -0.59
    POSITIVE LOGITS
    member
    1.47
    members
    1.47
    ors
    1.33
    or
    1.22
     chambers
    1.09
    woman
    1.05
    man
    0.99
     member
    0.99
     Member
    0.96
    walk
    0.95
    Activations Density 0.044%

    No Known Activations