© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1030
    Prev
    Next
    INDEX
    Explanations

    words containing the prefix "pre-"

    oai_token-act-pair · gpt-3.5-turbo

    the prefix "pre-" in various contexts

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

    No Comments

    Negative Logits
    loo
    -0.72
     Shack
    -0.67
    IBLE
    -0.66
    Ø©
    -0.65
     Cup
    -0.65
     Nig
    -0.64
     Hearts
    -0.63
     Slug
    -0.63
     Heights
    -0.62
     Ago
    -0.62
    POSITIVE LOGITS
    occup
    1.33
    requisites
    1.32
    ceed
    1.25
    fecture
    1.20
    req
    1.16
    occupied
    1.16
    hens
    1.13
    lude
    1.12
    achers
    1.12
    cession
    1.10
    Activations Density 0.022%

    No Known Activations