© 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. 10514
    Prev
    Next
    INDEX
    Explanations

    adjectives or adverbs describing intensity, emphasis, or qualities of actions

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that describe intensity or significance

    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
    anwhile
    -0.84
     Related
    -0.74
    estate
    -0.73
    ramid
    -0.72
    ounters
    -0.71
    ecycle
    -0.70
    ropolis
    -0.69
    ategories
    -0.67
    gey
    -0.67
    -+-+
    -0.66
    POSITIVE LOGITS
     impunity
    1.42
     ease
    1.33
     vig
    1.26
     precision
    1.22
     abandon
    1.22
     gust
    1.19
     haste
    1.15
     certainty
    1.14
     sincerity
    1.08
     frequency
    1.07
    Activations Density 0.209%

    No Known Activations