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. 8-RES-JB
    6. 15902
    Prev
    Next
    INDEX
    Explanations

    political statements or criticisms

    oai_token-act-pair · gpt-3.5-turbo

    elements related to political discourse and criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĥãĥĪ
    -0.68
    DragonMagazine
    -0.66
     prest
    -0.65
    utor
    -0.65
     Intake
    -0.64
    iple
    -0.63
     SERV
    -0.62
    INT
    -0.62
     ILCS
    -0.61
    Purchase
    -0.60
    POSITIVE LOGITS
     noting
    1.34
     saying
    1.32
     stating
    1.29
     citing
    1.12
     insisting
    1.11
     arguing
    0.99
     claiming
    0.99
     stressing
    0.97
     pointing
    0.94
     remark
    0.94
    Activations Density 0.587%

    No Known Activations