© 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. 8721
    Prev
    Next
    INDEX
    Explanations

    phrases related to software or programming commands

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the preposition "in."

    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
    scar
    -0.71
    0000000000000000
    -0.70
    ylum
    -0.68
    philis
    -0.67
    riots
    -0.66
    ugu
    -0.64
     incumb
    -0.64
    HAEL
    -0.63
    abilia
    -0.63
    killers
    -0.63
    POSITIVE LOGITS
     conjunction
    1.30
     lieu
    1.24
     accordance
    1.11
    between
    1.08
     order
    1.08
     addition
    1.05
     Settings
    1.03
     ~/.
    0.96
     relation
    0.95
     milliseconds
    0.94
    Activations Density 0.210%

    No Known Activations