© 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. 14148
    Prev
    Next
    INDEX
    Explanations

    words indicating future actions or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "be" and its variations in context

    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
     Genius
    -0.67
    ioch
    -0.65
    ciating
    -0.65
     ILCS
    -0.63
     imagination
    -0.63
     Pret
    -0.61
    ths
    -0.61
    Moon
    -0.60
    76561
    -0.60
     dots
    -0.59
    POSITIVE LOGITS
     able
    1.07
     someday
    0.95
     rewarded
    0.93
    fall
    0.91
    fitting
    0.89
     punished
    0.87
     repaid
    0.86
     alright
    0.83
     eaten
    0.81
     tolerated
    0.81
    Activations Density 0.202%

    No Known Activations