© 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. 7-RES-JB
    11. 13449
    Prev
    Next
    INDEX
    Explanations

    acronyms or specific capitalized terms

    oai_token-act-pair · gpt-3.5-turbo

    references to the abbreviation "CF" often related to a financial context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oppable
    -0.81
    rawdownloadcloneembedreportprint
    -0.80
    âĸ¬
    -0.68
    ãĤ°
    -0.68
     è£ıç
    -0.65
    heimer
    -0.64
     Gors
    -0.64
    sbm
    -0.63
    owsky
    -0.62
    selves
    -0.62
    POSITIVE LOGITS
    incinn
    0.86
    avorite
    0.82
    erm
    0.82
    ritical
    0.81
    arlane
    0.80
    ayette
    0.79
    ranch
    0.79
    DN
    0.79
    TC
    0.79
    WS
    0.79
    Activations Density 0.019%

    No Known Activations