© 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. 14338
    Prev
    Next
    INDEX
    Explanations

    verbs or phrases related to plans, intentions, or actions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of intent or desires related to actions or plans

    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
    glers
    -0.66
     themselves
    -0.66
    eers
    -0.65
     itself
    -0.63
     guiActiveUnfocused
    -0.63
    immers
    -0.62
     Bits
    -0.61
     populations
    -0.61
     unison
    -0.60
     Pse
    -0.59
    POSITIVE LOGITS
     personally
    1.20
    poke
    0.87
     resign
    0.82
     "#
    0.77
     himself
    0.74
     constituents
    0.72
    twitter
    0.70
    iden
    0.69
    realDonaldTrump
    0.67
     "'
    0.66
    Activations Density 0.612%

    No Known Activations