© 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. 3479
    Prev
    Next
    INDEX
    Explanations

    words related to being free or without something (e.g., "free", "less")

    oai_token-act-pair · gpt-3.5-turbo

    terms related to freedom or absence of restrictions

    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
    skilled
    -0.75
    INC
    -0.74
    foreseen
    -0.74
    NEWS
    -0.70
    ional
    -0.65
    part
    -0.64
    along
    -0.63
    achu
    -0.63
    shows
    -0.62
    skill
    -0.61
    POSITIVE LOGITS
    zing
    1.10
    zers
    0.95
    ze
    0.91
    lihood
    0.90
    zes
    0.87
    zer
    0.84
     zones
    0.78
     mentality
    0.77
     zone
    0.76
    zhen
    0.76
    Activations Density 0.099%

    No Known Activations