© 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. 18650
    Prev
    Next
    INDEX
    Explanations

    adjectives related to physical characteristics or qualities

    oai_token-act-pair · gpt-3.5-turbo

    adjectives describing various characteristics and qualities

    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
     accordingly
    -0.74
    `.
    -0.73
    SPONSORED
    -0.70
     Shards
    -0.68
    inctions
    -0.68
    .''.
    -0.67
     RELE
    -0.65
     Strongh
    -0.65
    Reloaded
    -0.65
    Tokens
    -0.65
    POSITIVE LOGITS
    -
    1.01
    bred
    0.98
    headed
    0.95
    faced
    0.94
    haired
    0.94
    hearted
    0.91
     blonde
    0.86
    looking
    0.86
     bearded
    0.85
    neck
    0.83
    Activations Density 0.346%

    No Known Activations