© 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. 3475
    Prev
    Next
    INDEX
    Explanations

    mentions of detailed objects, particularly those related to architecture, art, and physical environments

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

    references to vehicles, particularly cars and buses

    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
     Enlight
    -0.67
     defin
    -0.65
     Flavoring
    -0.61
     clarified
    -0.58
     Nicarag
    -0.58
     Tau
    -0.58
     Firearms
    -0.56
     Nug
    -0.56
     BET
    -0.55
     Princ
    -0.55
    POSITIVE LOGITS
    ousel
    1.37
    penter
    1.30
    riages
    1.26
    abin
    1.18
    oling
    1.18
    avan
    1.16
    olina
    1.15
    pent
    1.14
    negie
    1.10
    rots
    1.10
    Activations Density 0.049%

    No Known Activations