© 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. 7-RES-JB
    11. 14152
    Prev
    Next
    INDEX
    Explanations

    terms related to specific technologies or models, potentially relating to scientific research or procedures

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     cle
    -0.74
     gra
    -0.73
     jun
    -0.66
     chants
    -0.65
     âĵĺ
    -0.64
    assetsadobe
    -0.64
     Mum
    -0.63
     Lynd
    -0.60
    ãĤ§
    -0.60
     timet
    -0.59
    POSITIVE LOGITS
    PP
    0.98
    ISA
    0.95
    PN
    0.93
    CP
    0.92
    CS
    0.91
    VD
    0.91
    SF
    0.90
    GC
    0.89
    LP
    0.89
    APD
    0.87
    Activations Density 0.213%

    No Known Activations