© 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. 3162
    Prev
    Next
    INDEX
    Explanations

    words related to research "labs"

    oai_token-act-pair · gpt-3.5-turbo

    references to various laboratories and lab-related terms

    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
    BOOK
    -0.71
    making
    -0.70
    âĿ
    -0.68
    cho
    -0.64
    historic
    -0.64
    fulness
    -0.63
    \":
    -0.63
    natal
    -0.61
    cut
    -0.61
    birth
    -0.61
    POSITIVE LOGITS
     Labs
    1.35
     Laboratories
    1.28
    rador
    1.06
     labs
    0.99
     Associates
    0.94
    orer
    0.93
     laboratories
    0.79
     Laboratory
    0.77
    incinn
    0.77
    cius
    0.75
    Activations Density 0.007%

    No Known Activations