© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 15404
    Prev
    Next
    INDEX
    Explanations

    titles or roles related to communication and information dissemination in a political context

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals in press secretary roles

    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
     "$:/
    -0.75
    200000
    -0.68
    urat
    -0.63
    imoto
    -0.63
    ESE
    -0.62
    bilt
    -0.61
    soDeliveryDate
    -0.61
    é¾įå
    -0.60
     [|
    -0.59
     intest
    -0.59
    POSITIVE LOGITS
     Sean
    0.94
     Brendan
    0.88
     Dmitry
    0.85
     Steph
    0.83
     Katie
    0.82
     Brian
    0.82
     Natasha
    0.82
     Geoff
    0.80
     Lauren
    0.79
     Liz
    0.79
    Activations Density 0.088%

    No Known Activations