© 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. 12-RES-JB
    11. 2567
    Prev
    Next
    INDEX
    Explanations

    details about events or occurrences and time-specific information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases related to event cancellations and scheduling issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     Penet
    -0.76
    ecd
    -0.72
    asuring
    -0.71
    esting
    -0.71
    ĸļ
    -0.70
    Growing
    -0.67
    hov
    -0.67
    rowth
    -0.66
    ophile
    -0.65
    ©¶æ¥µ
    -0.65
    POSITIVE LOGITS
     postponed
    1.63
     postp
    1.62
     cancellation
    1.49
     scheduling
    1.47
     cancell
    1.45
     postpone
    1.43
     cancelled
    1.42
     canceled
    1.41
     cancel
    1.35
     cance
    1.31
    Activations Density 0.891%

    No Known Activations