© 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. 4718
    Prev
    Next
    INDEX
    Explanations

    phrases where there is a sense of uncertainty or disagreement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "neither" to express negation or contrast

    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
    soType
    -0.81
    Vers
    -0.75
    ahime
    -0.74
    uctions
    -0.72
    inav
    -0.71
    psc
    -0.69
    angan
    -0.68
    eln
    -0.68
    unc
    -0.67
    soc
    -0.67
    POSITIVE LOGITS
     sexes
    0.82
    theless
    0.81
    !--
    0.73
     overtly
    0.73
     sides
    0.71
     genders
    0.67
    icably
    0.66
    xious
    0.66
    lihood
    0.59
    ctor
    0.59
    Activations Density 0.007%

    No Known Activations