© 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. 9-RES-JB
    11. 16013
    Prev
    Next
    INDEX
    Explanations

    keywords relating to rules or guidelines

    oai_token-act-pair · gpt-3.5-turbo

    references to collective actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thirds
    -0.81
     Hasan
    -0.68
    FORE
    -0.67
     Lans
    -0.63
    butt
    -0.61
     Teresa
    -0.59
     Haram
    -0.57
     Cyrus
    -0.57
     Pound
    -0.57
     ashore
    -0.57
    POSITIVE LOGITS
    ions
    2.02
    ive
    2.01
    ively
    1.95
    ives
    1.90
    ivity
    1.76
    ors
    1.67
    iveness
    1.67
    ibles
    1.64
    ivist
    1.63
    ional
    1.62
    Activations Density 0.216%

    No Known Activations