© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 2283
    Prev
    Next
    INDEX
    Explanations

    descriptions of characteristics or elements that are seen as essential or integral to a particular experience or setting

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    references to measures of quantity, particularly in groupings or sets

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    mins
    -0.71
    DEN
    -0.61
    gone
    -0.58
     Drawn
    -0.58
    CHR
    -0.57
     secretaries
    -0.56
     Lyme
    -0.56
     Rao
    -0.55
    ãĤ¦ãĤ¹
    -0.54
     assistants
    -0.54
    POSITIVE LOGITS
    uple
    1.60
    essential
    1.52
    esson
    1.16
    ess
    1.08
    illions
    1.07
    etting
    1.05
    illion
    1.01
    et
    1.00
    agonal
    1.00
    ilian
    0.96
    Activations Density 0.046%

    No Known Activations