© 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. 3-RES-JB
    11. 11367
    Prev
    Next
    INDEX
    Explanations

    terms related to specific diseases or conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to specific risks, conditions, and entities in various contexts, especially those concerning public health, environmental issues, and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     âĢº
    -0.72
    orsche
    -0.64
    OOOO
    -0.59
    lihood
    -0.56
     automakers
    -0.55
    uay
    -0.55
    -------------
    -0.52
    product
    -0.51
    iott
    -0.51
    umbnails
    -0.51
    POSITIVE LOGITS
     conclud
    0.60
     rul
    0.58
     eternity
    0.57
     unworthy
    0.55
    fml
    0.55
    livion
    0.55
     elsewhere
    0.54
     footing
    0.54
    senal
    0.53
    strike
    0.53
    Activations Density 1.873%

    No Known Activations