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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 22978
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Another" followed by a description or noun

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "Another" indicating a list of additional points or examples

    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
    ouls
    -0.85
    hips
    -0.83
    riages
    -0.79
    bows
    -0.77
    opus
    -0.76
    anism
    -0.73
    onies
    -0.69
    olas
    -0.68
    rences
    -0.66
    ÃįÃį
    -0.66
    POSITIVE LOGITS
     reason
    1.09
     drawback
    1.07
     factor
    1.06
     aspect
    1.05
     notable
    1.05
     example
    1.03
     noteworthy
    1.01
     interesting
    0.99
     important
    0.98
     pecul
    0.98
    Activations Density 0.070%

    No Known Activations