© 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. 12-RES-JB
    11. 2708
    Prev
    Next
    INDEX
    Explanations

    references to blockchain technology companies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    mentions of "Bit" and related terms in the context of cryptocurrency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theless
    -0.64
     newer
    -0.61
     fumes
    -0.59
     Siber
    -0.59
     admissions
    -0.59
     contractor
    -0.58
     untold
    -0.58
     contributing
    -0.57
     facing
    -0.57
     sling
    -0.56
    POSITIVE LOGITS
    terness
    1.41
    Torrent
    1.27
    fine
    1.14
    wig
    1.12
    umen
    1.12
    buck
    1.08
    message
    1.05
    Instant
    1.02
    license
    1.00
    map
    1.00
    Activations Density 0.037%

    No Known Activations