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

    Neuronpedia

    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. 20736
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing importance or emphasis, similar to "last but not least."

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a condition of being the least or a notable degree of something

    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
    gypt
    -0.82
    oling
    -0.74
    «ĺ
    -0.65
    dayName
    -0.65
    ibal
    -0.64
    iHUD
    -0.63
     basal
    -0.62
    hare
    -0.62
    ptin
    -0.62
    perate
    -0.61
    POSITIVE LOGITS
    tarians
    0.72
    swick
    0.70
    atories
    0.68
    tons
    0.68
    */(
    0.66
    ANCE
    0.65
    iance
    0.64
     headers
    0.63
    culosis
    0.63
    iety
    0.61
    Activations Density 0.035%

    No Known Activations