© 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. 22732
    Prev
    Next
    INDEX
    Explanations

    expressions of emphasis or intensity

    oai_token-act-pair · gpt-3.5-turbo

    negations and phrases that convey a sense of denial or rejection

    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
    =-=-=-=-=-=-=-=-
    -0.78
     accommodation
    -0.71
     ItemLevel
    -0.66
     Carbuncle
    -0.65
    ersen
    -0.62
     Edited
    -0.62
     Mechdragon
    -0.62
    èĢħ
    -0.61
     Grimoire
    -0.60
    IAN
    -0.60
    POSITIVE LOGITS
    't
    1.09
    gin
    1.00
    strument
    0.90
    cause
    0.87
    nect
    0.86
    ned
    0.86
    ppo
    0.85
    ny
    0.83
    ighty
    0.83
    hers
    0.82
    Activations Density 0.016%

    No Known Activations