© 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. 10-RES-JB
    11. 24059
    Prev
    Next
    INDEX
    Explanations

    numerical values indicating quantities of people or groups

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various groups or quantities of people

    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
    ãĤ¦ãĤ¹
    -0.73
    ãĥĥ
    -0.67
    =~
    -0.62
     eternity
    -0.60
    YN
    -0.59
    senal
    -0.59
    tnc
    -0.57
    inventoryQuantity
    -0.55
    ãģĻ
    -0.55
    feeding
    -0.55
    POSITIVE LOGITS
     participated
    1.35
     perished
    1.30
     have
    1.23
     were
    1.23
     reside
    1.21
     died
    1.21
     are
    1.16
     specialize
    1.13
     remain
    1.12
     survived
    1.12
    Activations Density 0.300%

    No Known Activations