© 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. 7-RES-JB
    11. 3162
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "and."

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Deal
    -0.92
    dq
    -0.83
    Recomm
    -0.80
    bda
    -0.73
    zb
    -0.70
    inational
    -0.69
     psychiat
    -0.68
    Sov
    -0.68
    bub
    -0.66
    sylv
    -0.66
    POSITIVE LOGITS
    rogens
    1.02
    romeda
    1.00
    rogen
    0.88
     Other
    0.85
    ERSON
    0.84
    rew
    0.80
     Sons
    0.79
     Related
    0.73
     Beyond
    0.72
    uin
    0.71
    Activations Density 0.258%

    No Known Activations