© 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. 6-RES-JB
    11. 14068
    Prev
    Next
    INDEX
    Explanations

    positive and negative characteristics or attributes related to a person

    oai_token-act-pair · gpt-3.5-turbo

    attributes related to personalities and lifestyles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vier
    -0.71
    eeper
    -0.70
    ivably
    -0.69
    versely
    -0.68
     oneself
    -0.66
    untarily
    -0.65
    ificantly
    -0.64
    uine
    -0.62
    ilateral
    -0.61
    vell
    -0.60
    POSITIVE LOGITS
     counterparts
    0.85
    smanship
    0.78
     creations
    0.75
    powers
    0.73
     antics
    0.73
    nings
    0.72
     charms
    0.71
    mates
    0.68
    ulations
    0.68
     mates
    0.67
    Activations Density 0.394%

    No Known Activations