© 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 EvalsExportsinterp-engineNEWAPI 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. 5514
    Prev
    Next
    INDEX
    Explanations

    scientific research institutions or organizations

    oai_token-act-pair · gpt-3.5-turbo

    the recurrence of the phrase "at" in various contexts

    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
    ãĤ¼ãĤ¦ãĤ¹
    -0.84
    ãĢĤ
    -0.72
    VALUE
    -0.72
    TEXTURE
    -0.69
    ãĤ¦ãĤ¹
    -0.69
    ãĤĴ
    -0.68
     TAMADRA
    -0.68
    channelAvailability
    -0.66
    EStreamFrame
    -0.66
     ($)
    -0.65
    POSITIVE LOGITS
     Greenpeace
    0.73
    raq
    0.67
     Nanto
    0.67
    ongyang
    0.65
    vernment
    0.65
     Sloan
    0.64
    pired
    0.64
     Sac
    0.64
     Param
    0.64
     academia
    0.63
    Activations Density 0.211%

    No Known Activations