© 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. 13120
    Prev
    Next
    INDEX
    Explanations

    phrases with the expression "all" followed by an adjective or verb

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "all"

    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
    •All the Features!

    No Comments

    Negative Logits
    aminer
    -0.71
    bal
    -0.63
    chie
    -0.62
     reper
    -0.62
     Refer
    -0.57
    IDS
    -0.56
     Reprodu
    -0.56
    SHIP
    -0.56
    lav
    -0.56
    nom
    -0.54
    POSITIVE LOGITS
    igator
    1.08
    igators
    1.07
     kinds
    1.07
     sorts
    1.06
    ocating
    1.00
    ergic
    0.99
    udes
    0.94
    uring
    0.92
    ocated
    0.91
    usions
    0.91
    Activations Density 0.087%

    No Known Activations