© 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. 7555
    Prev
    Next
    INDEX
    Explanations

    adjectives related to levels or degrees of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate varying levels of intensity or measurement

    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
    ttes
    -0.77
    aired
    -0.74
    paces
    -0.74
    maid
    -0.73
    ãĤ¼
    -0.73
    wives
    -0.73
    books
    -0.72
    ores
    -0.71
    rams
    -0.71
    orative
    -0.70
    POSITIVE LOGITS
     sophistication
    1.42
     abstraction
    1.39
     maturity
    1.17
     scrutiny
    1.16
     intensity
    1.12
     professionalism
    1.11
     autonomy
    1.11
     complexity
    1.09
     confidence
    1.08
     involvement
    1.07
    Activations Density 0.081%

    No Known Activations