© 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. 5774
    Prev
    Next
    INDEX
    Explanations

    questions starting with "How can" or "How could"

    oai_token-act-pair · gpt-3.5-turbo

    questions that begin with "how can" or "how could."

    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
    hig
    -0.82
     teasp
    -0.79
    fax
    -0.78
    chnology
    -0.74
    xon
    -0.71
    paio
    -0.70
    minus
    -0.67
    combe
    -0.67
    ements
    -0.66
    ullivan
    -0.66
    POSITIVE LOGITS
     we
    1.02
     you
    0.93
     anyone
    0.93
     someone
    0.88
     they
    0.88
     anybody
    0.81
     this
    0.77
     somebody
    0.76
     outsiders
    0.72
     such
    0.72
    Activations Density 0.060%

    No Known Activations