© 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. 11995
    Prev
    Next
    INDEX
    Explanations

    phrases with special characters used purposefully to convey a specific meaning

    oai_token-act-pair · gpt-3.5-turbo

    the presence of unique or specialized symbols and characters

    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
     metic
    -0.89
     bubble
    -0.78
     Opinion
    -0.78
     calib
    -0.77
     hatch
    -0.74
     swarm
    -0.73
     consolation
    -0.72
     liner
    -0.72
     pronoun
    -0.72
     oun
    -0.71
    POSITIVE LOGITS
    especially
    1.62
    they
    1.62
    that
    1.62
    perhaps
    1.61
    their
    1.61
    particularly
    1.61
    meaning
    1.61
    including
    1.60
    the
    1.60
    either
    1.58
    Activations Density 0.099%

    No Known Activations