© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 7525
    Prev
    Next
    INDEX
    Explanations

    mentions of the concept of 'first'

    oai_token-act-pair · gpt-3.5-turbo

    references to first occurrences or milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    politics
    -0.77
    md
    -0.72
    lag
    -0.72
    til
    -0.71
    lang
    -0.67
    each
    -0.65
    rice
    -0.64
    behind
    -0.64
    PLIED
    -0.64
    along
    -0.63
    POSITIVE LOGITS
     glimpse
    1.02
     ever
    1.01
     batch
    0.97
     EVER
    0.91
     tentative
    0.83
     incarnation
    0.78
     foray
    0.77
     installment
    0.77
     casualty
    0.76
     baseman
    0.76
    Activations Density 0.088%

    No Known Activations