© 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. 11-RES-JB
    11. 12966
    Prev
    Next
    INDEX
    Explanations

    verbs or phrases indicating uncertainty or prediction in relation to future outcomes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to uncertainty about future outcomes and potential consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    noticed
    -0.67
     fractions
    -0.67
    quished
    -0.66
    Lyn
    -0.60
    Pal
    -0.59
    tun
    -0.58
     exited
    -0.57
     Vish
    -0.56
     dodged
    -0.56
     waited
    -0.56
    POSITIVE LOGITS
     entail
    1.26
     be
    1.08
     look
    1.01
     accomplish
    0.99
     achieve
    0.95
     involve
    0.93
     imply
    0.93
     consist
    0.89
     deliver
    0.87
     bring
    0.87
    Activations Density 0.092%

    No Known Activations