© 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. 22674
    Prev
    Next
    INDEX
    Explanations

    examples of words related to a specific person's name, "Kaitlin", though it also picks up "Kaitlyn" and "Kaitlyin" occasionally

    oai_token-act-pair · gpt-3.5-turbo

    the mention of "Kaitlin" 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
    sword
    -0.68
    oted
    -0.63
    ITED
    -0.61
     sliding
    -0.60
    ULT
    -0.59
    requires
    -0.58
    tty
    -0.58
     segregated
    -0.57
    wallet
    -0.57
    forced
    -0.57
    POSITIVE LOGITS
    anya
    0.89
    anooga
    0.86
    lyn
    0.82
     Sith
    0.79
    ait
    0.77
    rait
    0.77
    lin
    0.75
    endment
    0.74
    alon
    0.73
    eering
    0.73
    Activations Density 0.025%

    No Known Activations