© 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. 8-RES-JB
    11. 14258
    Prev
    Next
    INDEX
    Explanations

    names of people or characters

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the letter 'h' throughout the document

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Clicker
    -0.82
    aution
    -0.79
     Collider
    -0.72
     mosqu
    -0.72
    enhagen
    -0.70
    phrine
    -0.67
    ãĤ´ãĥ³
    -0.66
    eering
    -0.63
     destro
    -0.63
    eon
    -0.62
    POSITIVE LOGITS
    orses
    1.18
    ulk
    1.14
    agen
    1.14
    ulhu
    1.13
    awk
    1.13
    onest
    1.08
    ollow
    1.07
    undred
    1.05
    ackers
    1.05
    atever
    1.05
    Activations Density 0.051%

    No Known Activations