© 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. 4747
    Prev
    Next
    INDEX
    Explanations

    information about obscure or lesser-known entities or events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    information related to lesser-known entities or upcoming events

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    getic
    -0.56
    ISC
    -0.54
    ocene
    -0.53
    ctic
    -0.53
    gian
    -0.52
    incial
    -0.50
    amous
    -0.49
    erity
    -0.49
    FUL
    -0.48
    vernment
    -0.48
    POSITIVE LOGITS
     targ
    0.49
     challeng
    0.48
     referen
    0.42
     powd
    0.42
     Replay
    0.41
     Dise
    0.41
     guiActiveUnfocused
    0.40
     Cups
    0.40
     darts
    0.40
     Vengeance
    0.39
    Activations Density 1.424%

    No Known Activations