© 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. 3-RES-JB
    11. 17112
    Prev
    Next
    INDEX
    Explanations

    verbs related to changing or altering something

    oai_token-act-pair · gpt-3.5-turbo

    words that suggest defining, categorizing, or evaluating concepts or actions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     geared
    -0.61
    ritical
    -0.59
     spor
    -0.58
    oter
    -0.58
     unable
    -0.55
     vacuum
    -0.55
    omnia
    -0.55
     inexpl
    -0.54
     prow
    -0.54
    amar
    -0.53
    POSITIVE LOGITS
    uate
    0.96
    ments
    0.95
    ISE
    0.91
    ment
    0.91
    ably
    0.84
    UTE
    0.83
    INGS
    0.82
    ABLE
    0.79
    ATIONAL
    0.79
    ingly
    0.76
    Activations Density 0.098%

    No Known Activations