© 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. 3858
    Prev
    Next
    INDEX
    Explanations

    adjectives describing a wide variety or range of things

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases associated with diversity and variety

    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
    iddles
    -0.65
    ··
    -0.65
    vantage
    -0.63
    hops
    -0.62
    kamp
    -0.62
    offic
    -0.61
    UTC
    -0.60
    til
    -0.59
    Finish
    -0.59
    marks
    -0.58
    POSITIVE LOGITS
     assortment
    1.75
     array
    1.66
     number
    1.65
     amount
    1.46
     variety
    1.45
     plethora
    1.41
     range
    1.36
     multitude
    1.30
     slew
    1.30
     trove
    1.23
    Activations Density 0.341%

    No Known Activations