© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12111
    Prev
    Next
    INDEX
    Explanations

    phrases describing a specific type of experience or situation

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "one of those."

    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
    Rated
    -0.71
    BW
    -0.66
    aeus
    -0.66
     Akin
    -0.65
    vic
    -0.65
    èª
    -0.63
     Magnus
    -0.63
    kamp
    -0.62
    wt
    -0.62
    PART
    -0.62
    POSITIVE LOGITS
     pesky
    0.75
    devices
    0.69
     annoying
    0.68
     lucky
    0.68
     captcha
    0.68
     weird
    0.67
     runaway
    0.65
     quir
    0.65
     coma
    0.64
    few
    0.64
    Activations Density 0.044%

    No Known Activations