© 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. 0-RES-JB
    11. 20452
    Prev
    Next
    INDEX
    Explanations

    phrases related to the prefix "Bio"

    oai_token-act-pair · gpt-3.5-turbo

    references to biotechnology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤĭ
    -0.84
    aways
    -0.83
    çĭ
    -0.76
    manuel
    -0.73
    lehem
    -0.73
     rush
    -0.70
    pher
    -0.68
    hur
    -0.65
    shaw
    -0.64
    urst
    -0.64
    POSITIVE LOGITS
     Bi
    3.69
    Bi
    2.99
     bi
    2.18
     Bio
    2.12
    Bio
    1.85
    bi
    1.84
     Biological
    1.54
     biome
    1.48
     BI
    1.45
     Zo
    1.36
    Activations Density 0.018%

    No Known Activations