© 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. 11-RES-JB
    11. 9452
    Prev
    Next
    INDEX
    Explanations

    items listed in a ranking order

    oai_token-act-pair · gpt-3.5-turbo

    references to rankings or lists

    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
    ufact
    -0.62
    byter
    -0.62
     cov
    -0.60
    construct
    -0.59
    entimes
    -0.58
    ework
    -0.57
     subsistence
    -0.56
    isin
    -0.54
    />
    -0.54
     advers
    -0.54
    POSITIVE LOGITS
     category
    0.83
    heon
    0.80
     list
    0.79
    */(
    0.78
    Tier
    0.75
     lists
    0.73
     rankings
    0.73
     earners
    0.72
     alongside
    0.72
    elight
    0.71
    Activations Density 0.178%

    No Known Activations