© 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. 14294
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions that the speaker took or intended to take

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal accountability or responsibility

    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
     Their
    -0.67
    Available
    -0.65
    their
    -0.64
    Elsewhere
    -0.61
     respectively
    -0.61
    Their
    -0.59
     guiActiveUnfocused
    -0.58
     2018
    -0.57
     pricey
    -0.57
    WARE
    -0.57
    POSITIVE LOGITS
     myself
    1.44
     ['
    0.96
     my
    0.85
     [
    0.84
    %"
    0.77
    poke
    0.72
     âĢ¦"
    0.71
    oan
    0.68
     sacrific
    0.65
     coward
    0.65
    Activations Density 1.016%

    No Known Activations