© 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. 11-RES-JB
    11. 458
    Prev
    Next
    INDEX
    Explanations

    descriptions related to transformation, particularly into objects or situations

    oai_token-act-pair · gpt-3.5-turbo

    humorous and absurd elements in fictional narratives

    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
    isSpecialOrderable
    -0.87
    ilitation
    -0.81
    Reporting
    -0.80
    mediate
    -0.79
    Unity
    -0.77
    ESA
    -0.77
    gression
    -0.77
    ourses
    -0.75
     outset
    -0.75
    yssey
    -0.75
    POSITIVE LOGITS
     boobs
    1.31
     tattoos
    1.23
     tacos
    1.12
     creepy
    1.12
     dick
    1.11
     tits
    1.09
     bunny
    1.07
     lizard
    1.07
     poop
    1.06
     mustache
    1.06
    Activations Density 0.709%

    No Known Activations