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

    Neuronpedia

    Jacobian LensNEW
    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. 2363
    Prev
    Next
    INDEX
    Explanations

    references to individuals named "Dan."

    oai_token-act-pair · gpt-3.5-turbo

    the token used to denote end-of-text in various contexts

    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
    llor
    -0.72
     extremes
    -0.66
    CLASSIFIED
    -0.63
     membr
    -0.62
     margins
    -0.62
    Reloaded
    -0.61
    */(
    -0.61
     conspicuous
    -0.61
     imperson
    -0.61
     unaccount
    -0.60
    POSITIVE LOGITS
    zig
    1.37
    forth
    1.35
    ilo
    1.11
    coni
    1.04
    ube
    1.02
    wei
    1.02
    ica
    0.96
    alog
    0.95
     Rather
    0.92
    iken
    0.92
    Activations Density 0.017%

    No Known Activations