© 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. 14146
    Prev
    Next
    INDEX
    Explanations

    short text snippets containing references to various events or occurrences

    oai_token-act-pair · gpt-3.5-turbo

    instances of commas or punctuation related to lists or sequences

    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
    ire
    -0.67
    hub
    -0.65
    izen
    -0.62
    IENT
    -0.61
    ":"/
    -0.61
    isy
    -0.61
    yon
    -0.59
    ?]
    -0.58
    arie
    -0.58
    pec
    -0.58
    POSITIVE LOGITS
     resulting
    1.12
     wherein
    1.06
     causing
    1.04
     allowing
    1.03
     featuring
    1.01
     culminating
    0.99
     revealing
    0.99
     showcasing
    0.97
     demonstrating
    0.94
     enabling
    0.93
    Activations Density 0.455%

    No Known Activations