© 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. 10-RES-JB
    11. 13810
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussions and negotiations

    oai_token-act-pair · gpt-3.5-turbo

    instances of conjunctions or transitional phrases, particularly those indicating contrast or sequence in discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è£ħ
    -0.67
    robe
    -0.66
    arted
    -0.65
    ãĥĩ
    -0.64
    ahan
    -0.60
    gres
    -0.60
    eware
    -0.60
    versive
    -0.59
    ?????-?????-
    -0.59
    ighed
    -0.58
    POSITIVE LOGITS
     albeit
    1.17
     because
    1.04
     although
    1.02
     but
    1.02
     insofar
    0.96
     thanks
    0.95
    because
    0.95
     namely
    0.94
     yes
    0.93
     alas
    0.92
    Activations Density 0.289%

    No Known Activations