© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 6961
    Prev
    Next
    INDEX
    Explanations

    adverbs describing the degree or manner of an action

    oai_token-act-pair · gpt-3.5-turbo

    words that indicate recurrence or ongoing actions/events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =-=-=-=-=-=-=-=-
    -0.66
    rued
    -0.61
    orate
    -0.59
    scribe
    -0.57
    ashtra
    -0.56
    ursed
    -0.55
    aceae
    -0.55
    tted
    -0.54
     Freak
    -0.54
     Valhalla
    -0.54
    POSITIVE LOGITS
     owning
    1.49
     agreeing
    1.44
    having
    1.42
     having
    1.42
     adopting
    1.42
     needing
    1.41
     possessing
    1.40
     completing
    1.39
     realizing
    1.37
     acknowledging
    1.36
    Activations Density 0.232%

    No Known Activations