© 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 EvalsExportsAPI 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. 3981
    Prev
    Next
    INDEX
    Explanations

    the concept of being prepared or ready for a particular action or outcome

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "poised" and its context indicating readiness or expectation

    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
    bey
    -0.70
    cause
    -0.67
    cott
    -0.63
    Article
    -0.62
    GS
    -0.61
     CLSID
    -0.60
    EVA
    -0.60
    д
    -0.60
    tein
    -0.59
    ravings
    -0.59
    POSITIVE LOGITS
    abouts
    0.87
     poised
    0.80
    rons
    0.80
    cture
    0.76
    ebus
    0.76
     unbeliev
    0.76
    olicy
    0.72
    terday
    0.69
     posture
    0.69
    atoon
    0.68
    Activations Density 0.011%

    No Known Activations