© 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. 20809
    Prev
    Next
    INDEX
    Explanations

    verbs indicating future actions or intentions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express intentions or plans

    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
     Leban
    -0.73
    pires
    -0.69
    eatures
    -0.65
    anooga
    -0.64
    selves
    -0.63
     Apart
    -0.58
    senal
    -0.58
     Comes
    -0.58
    Lot
    -0.56
     yourselves
    -0.56
    POSITIVE LOGITS
     myself
    1.28
     write
    1.09
     confess
    1.06
     rant
    1.04
     admit
    1.02
     recommend
    0.96
     dedicate
    0.92
     apologise
    0.91
     apologize
    0.90
     reiterate
    0.89
    Activations Density 0.271%

    No Known Activations