© 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. 4884
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific actions or processes

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

    words related to preconceptions and challenges

    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
    ulence
    -0.70
     entirety
    -0.66
     masculinity
    -0.64
     Curve
    -0.64
     legitimacy
    -0.64
     absurdity
    -0.61
     totality
    -0.61
     interchange
    -0.61
     simplicity
    -0.60
     Conflict
    -0.59
    POSITIVE LOGITS
    elected
    1.16
    ivating
    1.14
    ivated
    1.14
    racted
    1.11
    angering
    1.08
    alysed
    1.07
    appointed
    1.05
    iliated
    1.05
    uned
    1.04
    cerned
    1.02
    Activations Density 0.393%

    No Known Activations