© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3360
    Prev
    Next
    INDEX
    Explanations

    phrases related to announcements or predictions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating predictions or expectations about future events

    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
    ahime
    -0.77
     IG
    -0.77
    lamm
    -0.77
    lik
    -0.77
     te
    -0.72
    jing
    -0.72
     Deng
    -0.71
    empl
    -0.70
    ii
    -0.69
    ieg
    -0.68
    POSITIVE LOGITS
     Per
    2.34
    Per
    2.29
     Perry
    1.93
    per
    1.77
     PER
    1.76
     Perkins
    1.75
    PER
    1.59
     Perl
    1.51
     Peru
    1.38
     Percy
    1.38
    Activations Density 0.158%

    No Known Activations