© 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. 3545
    Prev
    Next
    INDEX
    Explanations

    information related to specific materials and construction techniques, particularly in the context of baths or objects like metal boxes and dice

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

    specific materials and their combinations used in various contexts

    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
     precincts
    -0.87
     adolesc
    -0.85
     administrative
    -0.83
     variance
    -0.82
     Creator
    -0.81
     locality
    -0.81
     constitu
    -0.81
     totality
    -0.81
     adoption
    -0.81
     deductions
    -0.81
    POSITIVE LOGITS
    colored
    1.76
    skinned
    1.68
    fram
    1.62
    covered
    1.62
    shaped
    1.57
    lined
    1.56
    bodied
    1.55
    painted
    1.55
    edged
    1.53
    yellow
    1.51
    Activations Density 0.090%

    No Known Activations