© 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. 9-RES-JB
    11. 18645
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific person, likely Gall

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Gall" 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
    CLASSIFIED
    -0.64
    BOOK
    -0.63
    BLIC
    -0.62
     reality
    -0.59
    lly
    -0.58
    ccording
    -0.57
     wink
    -0.56
    ding
    -0.55
     Deal
    -0.55
     Arabian
    -0.54
    POSITIVE LOGITS
    agher
    1.27
    oway
    1.14
    eries
    1.10
    atin
    1.06
    oping
    1.05
    ophon
    1.04
    antry
    1.03
    ophone
    1.00
    esian
    0.96
    oons
    0.96
    Activations Density 0.047%

    No Known Activations