© 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. 11-RES-JB
    11. 21092
    Prev
    Next
    INDEX
    Explanations

    greetings and welcomes in text

    oai_token-act-pair · gpt-3.5-turbo

    the presence of punctuation marks, particularly commas and exclamation points

    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
    ___
    -0.76
    odo
    -0.70
    Nonetheless
    -0.70
    enger
    -0.67
    Others
    -0.67
    Parameters
    -0.67
    odes
    -0.65
    endish
    -0.63
    amount
    -0.62
    ei
    -0.62
    POSITIVE LOGITS
     featuring
    1.05
     showcasing
    0.95
     aka
    0.93
     wherein
    0.92
     where
    0.90
     LLC
    0.88
    feat
    0.87
     courtesy
    0.84
     Featuring
    0.83
     Inc
    0.78
    Activations Density 0.297%

    No Known Activations