© 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. 2-RES-JB
    11. 24184
    Prev
    Next
    INDEX
    Explanations

    keywords related to environmental cleanliness and regulations

    oai_token-act-pair · gpt-3.5-turbo

    references to "clean" in relation to environmental policies and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yip
    -0.78
    isSpecialOrderable
    -0.75
    eryl
    -0.72
    doms
    -0.72
    Bone
    -0.68
    pton
    -0.66
    iety
    -0.65
    ONT
    -0.65
    iage
    -0.65
    wegian
    -0.63
    POSITIVE LOGITS
     Clean
    1.16
     Explicit
    0.93
    liness
    0.82
    Clean
    0.82
    clean
    0.79
     Checks
    0.78
     cleaner
    0.77
    ing
    0.75
     Space
    0.72
     Sweep
    0.71
    Activations Density 0.003%

    No Known Activations