© 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. 10773
    Prev
    Next
    INDEX
    Explanations

    locations and proper names containing the substring "aya"

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of the substring "aya" 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
    ringe
    -0.96
    ipeg
    -0.86
    meet
    -0.81
    natureconservancy
    -0.80
    clerosis
    -0.79
    safe
    -0.76
    kes
    -0.74
    thora
    -0.73
    urgy
    -0.71
    erences
    -0.71
    POSITIVE LOGITS
    UAL
    1.00
    ModLoader
    0.81
    uality
    0.76
     Palace
    0.76
    ours
    0.72
     suites
    0.66
     Fathers
    0.65
     Oriental
    0.65
    agate
    0.64
    ored
    0.63
    Activations Density 0.072%

    No Known Activations