© 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. 19920
    Prev
    Next
    INDEX
    Explanations

    words related to successful or popular things, such as "hit"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "hit" 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
    æ©Ł
    -0.70
     Warm
    -0.66
    pires
    -0.63
     Rae
    -0.63
    UTH
    -0.62
    otive
    -0.62
     Philos
    -0.61
    undy
    -0.60
     Princ
    -0.60
    å¸
    -0.60
    POSITIVE LOGITS
    chens
    1.19
    ched
    1.09
    achi
    1.09
    ches
    1.08
    boxes
    1.00
    box
    0.98
    tle
    0.96
    ters
    0.92
    ting
    0.82
    terness
    0.81
    Activations Density 0.034%

    No Known Activations