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. 10-RES-JB
    6. 634
    Prev
    Next
    INDEX
    Explanations

    phrases related to seeking trust in news or information

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to seeking trustworthy news

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     polyg
    -0.59
    DonaldTrump
    -0.58
    asers
    -0.57
    geries
    -0.57
     Artists
    -0.55
    teenth
    -0.55
    ahan
    -0.55
    gal
    -0.54
    aceae
    -0.53
    uay
    -0.53
    POSITIVE LOGITS
     trust
    0.63
    edia
    0.59
     trusted
    0.56
    LI
    0.54
     trustworthy
    0.53
     Valiant
    0.52
    lore
    0.52
    ribute
    0.50
    igger
    0.50
    ainment
    0.50
    Activations Density 0.048%

    No Known Activations