© 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. 3-RES-JB
    11. 17513
    Prev
    Next
    INDEX
    Explanations

    expressions indicating anticipation or excitement for future events or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    expressions of anticipation or expectation about the future

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cius
    -0.74
    aples
    -0.70
    colo
    -0.67
    AKING
    -0.65
    hel
    -0.64
    rip
    -0.63
    anch
    -0.63
    MT
    -0.63
    azo
    -0.61
     Zombies
    -0.61
    POSITIVE LOGITS
    WARD
    0.94
    xual
    0.84
     puberty
    0.80
     pronouns
    0.79
    forward
    0.76
    wards
    0.76
     forward
    0.76
    Forward
    0.72
    isphere
    0.70
    olicy
    0.69
    Activations Density 0.010%

    No Known Activations