© 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. 7-RES-JB
    11. 17160
    Prev
    Next
    INDEX
    Explanations

    Wellness and health-related terms, particularly related to specific brands or organizations in the wellness industry

    oai_token-act-pair · gpt-3.5-turbo

    names of organizations and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.84
    anwhile
    -0.65
     quo
    -0.64
    etheless
    -0.59
     rul
    -0.58
     destro
    -0.58
    */(
    -0.57
     referen
    -0.56
     ---------
    -0.54
    raints
    -0.53
    POSITIVE LOGITS
     Brewing
    0.79
    Fest
    0.76
    Stream
    0.74
     Creek
    0.73
    Nation
    0.71
    Hack
    0.71
    Coin
    0.70
     Street
    0.69
    Sport
    0.68
    Star
    0.68
    Activations Density 0.637%

    No Known Activations