© 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. 2855
    Prev
    Next
    INDEX
    Explanations

    technical information and terms

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to approval and acceptance within various societal and technological 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
    escription
    -0.74
    ij士
    -0.62
    ãĥķãĤ¡
    -0.59
    CLASSIFIED
    -0.59
    ITNESS
    -0.58
    ÃįÃį
    -0.57
    sle
    -0.56
    Ô
    -0.56
     Adin
    -0.55
     earthqu
    -0.55
    POSITIVE LOGITS
     ensures
    1.24
     undermines
    1.18
     violates
    1.17
     constitutes
    1.13
     requires
    1.11
     eliminates
    1.10
     yields
    1.09
     ignores
    1.09
     lends
    1.08
     would
    1.07
    Activations Density 0.347%

    No Known Activations