© 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. 1-RES-JB
    11. 24194
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Micro" followed by a single-digit number

    oai_token-act-pair · gpt-3.5-turbo

    references to "Micro" structures or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UTC
    -0.70
     refrain
    -0.69
    swick
    -0.67
     rave
    -0.66
    enburg
    -0.66
    æĢ
    -0.64
    ILLE
    -0.64
    ============
    -0.63
    UAL
    -0.62
    »
    -0.62
    POSITIVE LOGITS
    bial
    1.41
    biology
    1.04
    Micro
    0.98
    phies
    0.95
    organisms
    0.95
    ropolitan
    0.92
     Micro
    0.91
     spores
    0.89
    iltr
    0.89
    plates
    0.88
    Activations Density 0.009%

    No Known Activations