© 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. 12620
    Prev
    Next
    INDEX
    Explanations

    instances of actions related to movement

    oai_token-act-pair · gpt-3.5-turbo

    the verb "get" in various forms and 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
     Inher
    -0.71
     Fail
    -0.71
     Rect
    -0.68
    NESS
    -0.65
    è¦ļéĨĴ
    -0.63
     Archdemon
    -0.62
     Recession
    -0.61
     Implementation
    -0.61
     Growth
    -0.60
     Surviv
    -0.59
    POSITIVE LOGITS
     rid
    1.00
     acquainted
    0.94
     closer
    0.93
    away
    0.92
     nearer
    0.90
     tangled
    0.90
     into
    0.89
     stuck
    0.88
     onto
    0.86
     away
    0.84
    Activations Density 0.080%

    No Known Activations