© 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. 10-RES-JB
    11. 18823
    Prev
    Next
    INDEX
    Explanations

    details about people and places, particularly focusing on events and descriptions

    oai_token-act-pair · gpt-3.5-turbo

    references to specific people, places, and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    clusive
    -0.68
    animate
    -0.64
    >[
    -0.61
    ilion
    -0.61
    ĵ
    -0.60
    plete
    -0.58
    IFF
    -0.57
    ãĥij
    -0.57
     DRAG
    -0.57
    oppable
    -0.56
    POSITIVE LOGITS
     agrees
    1.44
     testified
    1.37
     commented
    1.36
     remembers
    1.36
     tells
    1.35
     remarked
    1.31
     disagrees
    1.31
     believes
    1.29
     thinks
    1.29
     wrote
    1.28
    Activations Density 0.475%

    No Known Activations