© 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. 13592
    Prev
    Next
    INDEX
    Explanations

    numbers, specifically integers

    oai_token-act-pair · gpt-3.5-turbo

    present tense and continuous forms of the verb "to be."

    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
     Tycoon
    -0.79
     Fail
    -0.67
     sabotage
    -0.66
     retaliate
    -0.65
     competitor
    -0.63
    âķIJ
    -0.63
     breakup
    -0.62
     Gutenberg
    -0.61
     termination
    -0.60
     cooperate
    -0.60
    POSITIVE LOGITS
     witnessing
    1.09
     reminded
    1.05
     hearing
    1.04
     priv
    0.98
     greeted
    0.97
     noticing
    0.96
     expecting
    0.94
     pict
    0.93
     told
    0.93
     misled
    0.93
    Activations Density 0.190%

    No Known Activations