© 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. 20457
    Prev
    Next
    INDEX
    Explanations

    words related to maintenance and upkeep

    oai_token-act-pair · gpt-3.5-turbo

    words associated with positive states or conditions related to well-being and safety

    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
     DRAG
    -0.67
    bet
    -0.62
    calling
    -0.61
    imilar
    -0.59
    ASC
    -0.58
    asel
    -0.58
     descending
    -0.58
    FER
    -0.57
    abase
    -0.56
    fits
    -0.56
    POSITIVE LOGITS
     whilst
    0.76
     till
    0.73
    enged
    0.71
     indefinitely
    0.70
     ashore
    0.70
     until
    0.69
    ogether
    0.66
     despite
    0.66
     intact
    0.65
    iris
    0.65
    Activations Density 0.110%

    No Known Activations