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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    11. 11381
    Prev
    Next
    INDEX
    Explanations

    mentions of carnivals or related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to carnivals and specific brands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ansky
    -0.80
    essen
    -0.79
     Pants
    -0.77
     GPS
    -0.76
    ãĥĩãĤ£
    -0.73
    isSpecialOrderable
    -0.73
    uggle
    -0.69
    Browser
    -0.68
    tumblr
    -0.67
     Handler
    -0.66
    POSITIVE LOGITS
     carn
    2.78
     Carn
    1.99
    anth
    1.64
     Petro
    1.62
    Anth
    1.45
     Anth
    1.31
     Cann
    1.24
     anth
    1.23
     Carnival
    1.21
     Dion
    1.09
    Activations Density 0.041%

    No Known Activations