© 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. 1-RES-JB
    11. 20417
    Prev
    Next
    INDEX
    Explanations

    words related to names and labels

    oai_token-act-pair · gpt-3.5-turbo

    words related to naming or renaming

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     tremend
    -0.69
     confir
    -0.68
     nib
    -0.65
     holster
    -0.64
     denial
    -0.63
     prescription
    -0.61
     incon
    -0.61
     bondage
    -0.60
     retreating
    -0.59
     rehab
    -0.59
    POSITIVE LOGITS
    aming
    1.51
    ame
    1.44
    ames
    1.35
    amed
    1.25
    fleet
    0.98
    amia
    0.97
    AME
    0.91
    amn
    0.89
    plates
    0.83
    erous
    0.82
    Activations Density 0.005%

    No Known Activations