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

    Neuronpedia

    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. 4-RES-JB
    11. 609
    Prev
    Next
    INDEX
    Explanations

    words related to objections or disagreements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "objection" and its variants

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

    No Comments

    Negative Logits
     Tycoon
    -0.80
    rene
    -0.70
    estones
    -0.69
    oiler
    -0.67
    bered
    -0.66
    mingham
    -0.66
    estone
    -0.66
    ching
    -0.64
    roc
    -0.64
    mberg
    -0.63
    POSITIVE LOGITS
    naires
    1.01
     objections
    0.93
     thereto
    0.84
     vehemently
    0.79
     objection
    0.78
    ¿½
    0.77
     stren
    0.76
    aires
    0.73
    naire
    0.73
    ĸļ
    0.69
    Activations Density 0.021%

    No Known Activations