© 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. 0-RES-JB
    11. 1214
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to people

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Loren."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Channel
    -0.69
     property
    -0.68
     Cause
    -0.67
     slip
    -0.63
     bail
    -0.62
     Scotland
    -0.62
     tea
    -0.62
     themselves
    -0.62
     medium
    -0.61
     selfies
    -0.61
    POSITIVE LOGITS
    oren
    4.44
    ore
    1.47
     Loren
    1.30
    osen
    1.28
    orean
    1.20
    orie
    1.16
    orne
    1.14
    aren
    1.13
    olen
    1.12
    oret
    1.11
    Activations Density 0.014%

    No Known Activations