© 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. 10-RES-JB
    11. 18617
    Prev
    Next
    INDEX
    Explanations

    comparative adverbs indicating an increase or intensification

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express comparisons or increments in degree

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iversary
    -0.81
    ulia
    -0.74
    ãĥ¼ãĥĨãĤ£
    -0.73
    VIDIA
    -0.73
    éŃĶ
    -0.72
    ramid
    -0.70
     premie
    -0.70
     Landing
    -0.70
     VIDEOS
    -0.68
    ãĥ¯
    -0.67
    POSITIVE LOGITS
     interested
    1.43
     aware
    1.40
     wary
    1.39
     reluctant
    1.36
     cautious
    1.35
     confident
    1.34
     willing
    1.34
     adamant
    1.34
     hesitant
    1.32
     concerned
    1.31
    Activations Density 0.169%

    No Known Activations