© 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. 11-RES-JB
    11. 13504
    Prev
    Next
    INDEX
    Explanations

    sequential steps or instructions in a process

    oai_token-act-pair · gpt-3.5-turbo

    the verb "is" and its various forms, highlighting their usage in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    Merit
    -0.75
    Others
    -0.69
    ventures
    -0.68
    luaj
    -0.66
    ForgeModLoader
    -0.63
    nob
    -0.63
    vec
    -0.61
    "},"
    -0.61
    issues
    -0.61
    isine
    -0.60
    POSITIVE LOGITS
     analogous
    1.07
     comprised
    1.02
     used
    1.01
     where
    0.99
     optional
    0.98
     why
    0.95
     meant
    0.94
     usually
    0.93
     equivalent
    0.91
     responsible
    0.91
    Activations Density 0.222%

    No Known Activations