© 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. 11-RES-JB
    11. 3651
    Prev
    Next
    INDEX
    Explanations

    phrases related to preventing or avoiding situations

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases that start with "pre."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     laughter
    -0.72
    IBLE
    -0.67
     GOODMAN
    -0.66
    iveness
    -0.64
     lure
    -0.62
    ãĤ¼ãĤ¦ãĤ¹
    -0.61
     dots
    -0.61
    ourcing
    -0.59
    adia
    -0.58
    affe
    -0.57
    POSITIVE LOGITS
    pared
    1.56
    cision
    1.56
    cious
    1.48
    cise
    1.47
    requisite
    1.35
    requisites
    1.31
    ferred
    1.27
    jud
    1.24
    acher
    1.24
    historic
    1.23
    Activations Density 0.020%

    No Known Activations