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. 19084
    Prev
    Next
    INDEX
    Explanations

    specific mentions of "SC" or "Southern Counties" in the text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "SC" and its variations in context

    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
    hs
    -0.78
    cies
    -0.73
    ting
    -0.68
    zzle
    -0.67
    htar
    -0.66
     dab
    -0.63
     balloons
    -0.62
     stopp
    -0.60
    lihood
    -0.59
    che
    -0.59
    POSITIVE LOGITS
    ategory
    1.28
    RIPT
    1.25
    ORE
    1.24
    RIP
    1.14
    ustom
    1.10
    IENCE
    1.09
    OTUS
    1.09
    ANN
    1.08
    OTT
    1.08
    ODE
    1.07
    Activations Density 0.067%

    No Known Activations