© 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. 11-RES-JB
    11. 6915
    Prev
    Next
    INDEX
    Explanations

    phrases related to biology and biomedical science

    oai_token-act-pair · gpt-3.5-turbo

    terms related to molecular biology and genetic regulation

    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
     stra
    -0.73
     Stra
    -0.71
     humble
    -0.70
    Stra
    -0.65
     fame
    -0.65
     anniversary
    -0.64
     smack
    -0.63
     lounge
    -0.63
     vault
    -0.63
     crane
    -0.62
    POSITIVE LOGITS
    oxicity
    1.27
    oxic
    1.21
    ascular
    1.15
    immune
    1.13
    llular
    1.11
    zyme
    1.09
    activation
    1.09
    rotein
    1.09
    icrobial
    1.07
    rogens
    1.06
    Activations Density 0.155%

    No Known Activations