© 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. 2805
    Prev
    Next
    INDEX
    Explanations

    fractions

    oai_token-act-pair · gpt-3.5-turbo

    numerical values associated with measurements or quantities

    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
     impart
    -0.63
     prisons
    -0.59
     dear
    -0.58
     programming
    -0.56
     brid
    -0.56
     sensitive
    -0.55
     orchestr
    -0.55
     Holocaust
    -0.54
     shutter
    -0.54
     Fall
    -0.53
    POSITIVE LOGITS
    âģ
    0.83
    conom
    0.80
    ths
    0.76
    oplan
    0.75
    \\\\\\\\
    0.72
    ities
    0.71
    nder
    0.70
    /$
    0.68
    estone
    0.68
    estones
    0.68
    Activations Density 0.086%

    No Known Activations