© 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. 10037
    Prev
    Next
    INDEX
    Explanations

    locations or organizations where individuals are based

    oai_token-act-pair · gpt-3.5-turbo

    corporate affiliation or location phrases

    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
    é¾įå
    -0.76
    actual
    -0.64
     stub
    -0.64
    ingly
    -0.61
    assic
    -0.60
    ebin
    -0.58
    assian
    -0.57
    TPPStreamerBot
    -0.57
    latest
    -0.57
    ogue
    -0.56
    POSITIVE LOGITS
     abroad
    0.95
    illac
    0.84
     overseas
    0.81
     atop
    0.76
    atively
    0.75
     elsewhere
    0.73
     upon
    0.72
     loosely
    0.70
     downstairs
    0.70
     southeast
    0.70
    Activations Density 0.034%

    No Known Activations