© 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. 8-RES-JB
    11. 22260
    Prev
    Next
    INDEX
    Explanations

    adjectives or phrases related to the intensity or significance of a situation

    oai_token-act-pair · gpt-3.5-turbo

    adjectives and descriptors related to intensity or importance of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bots
    -0.96
    chairs
    -0.93
    masters
    -0.82
     Committees
    -0.77
    bows
    -0.76
    boats
    -0.75
    utics
    -0.73
    alysis
    -0.73
    wolves
    -0.72
    ttes
    -0.72
    POSITIVE LOGITS
     thing
    1.27
     piece
    1.26
     hurdle
    1.15
     outing
    1.06
     iteration
    1.04
     installment
    1.03
     item
    1.01
     step
    1.00
     foray
    0.99
     contender
    0.99
    Activations Density 0.339%

    No Known Activations