© 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. 10-RES-JB
    11. 14152
    Prev
    Next
    INDEX
    Explanations

    conjunctions and pronouns denoting involvement or responsibility

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and their actions within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arious
    -0.64
    jun
    -0.63
    Family
    -0.63
    course
    -0.61
    170
    -0.61
    detail
    -0.59
    00000
    -0.59
    uku
    -0.59
    requency
    -0.58
    ene
    -0.58
    POSITIVE LOGITS
     drew
    0.98
     coined
    0.94
     mattered
    0.93
     drove
    0.90
     decides
    0.89
     initiated
    0.88
     oversaw
    0.87
     prompted
    0.87
     determines
    0.87
     sparked
    0.87
    Activations Density 0.099%

    No Known Activations