© 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. 7-RES-JB
    11. 22326
    Prev
    Next
    INDEX
    Explanations

    phrases related to searching or seeking

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to seeking improvement and positive interactions

    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
    ettlement
    -0.73
    adobe
    -0.66
    fell
    -0.61
    dm
    -0.61
    hab
    -0.60
    ·
    -0.58
    DIT
    -0.58
     Rehab
    -0.57
    ð
    -0.57
     CLSID
    -0.56
    POSITIVE LOGITS
    ministic
    0.77
    enos
    0.70
     surprises
    0.70
    theless
    0.66
    andro
    0.64
     pursu
    0.63
     rhythms
    0.63
     pegged
    0.62
    .--
    0.61
    ursed
    0.61
    Activations Density 0.195%

    No Known Activations