© 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. 5631
    Prev
    Next
    INDEX
    Explanations

    words related to geographical locations, particularly ones with the common string "ark"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ark" 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
     Romeo
    -0.64
     unnecess
    -0.64
    ppo
    -0.61
    ahon
    -0.59
    ISTER
    -0.58
    æĺ
    -0.57
     livest
    -0.56
    ãģŁ
    -0.56
     sund
    -0.55
     reckoned
    -0.55
    POSITIVE LOGITS
    ansas
    1.28
    ozy
    1.24
    enment
    0.95
    ulic
    0.92
    anian
    0.91
    itect
    0.90
    eting
    0.87
    ness
    0.86
    entin
    0.86
    mares
    0.81
    Activations Density 0.024%

    No Known Activations