© 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. 10-RES-JB
    11. 21519
    Prev
    Next
    INDEX
    Explanations

    symbols (Ċ, Ŀ, âĢ, âľ, âĢĵ, âĢħ) used as separators or markers in the text

    oai_token-act-pair · gpt-3.5-turbo

    indicators of performance metrics or numerical data related to organizations or activities

    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
     footing
    -0.65
     obscurity
    -0.61
    collar
    -0.57
     whereabouts
    -0.57
    ometimes
    -0.55
     Tornado
    -0.54
    lections
    -0.54
     dazz
    -0.53
     loneliness
    -0.53
     dating
    -0.53
    POSITIVE LOGITS
    ³³³³³³³³³³³³³³³³
    0.76
    Furthermore
    0.75
    ³³³³³³³³
    0.71
    null
    0.69
    ³³³³
    0.67
    However
    0.67
    Nonetheless
    0.66
    Shape
    0.66
    Moreover
    0.65
    Likewise
    0.65
    Activations Density 0.341%

    No Known Activations