© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 4761
    Prev
    Next
    INDEX
    Explanations

    financial and numerical information like amounts, percentages, and quantities

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to statistics and measurements

    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
     opio
    -0.65
    ĨĴ
    -0.60
     Gors
    -0.58
     repertoire
    -0.57
    ouver
    -0.56
    ipedia
    -0.52
     cheesy
    -0.51
     clipboard
    -0.51
     proactive
    -0.51
     Tah
    -0.51
    POSITIVE LOGITS
     respectively
    1.33
    .
    0.99
    +.
    0.95
    .).
    0.78
    ."
    0.78
    ).
    0.76
     Lastly
    0.75
    .''.
    0.75
    )).
    0.74
    ;
    0.74
    Activations Density 0.455%

    No Known Activations