© 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. 5427
    Prev
    Next
    INDEX
    Explanations

    names or components of names that include "esh"

    oai_token-act-pair · gpt-3.5-turbo

    names or titles that end with similar sounds

    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
    eering
    -0.71
     caring
    -0.66
     Lethal
    -0.56
     Mother
    -0.55
     numbered
    -0.55
    stress
    -0.54
     lockdown
    -0.54
    activation
    -0.53
    esters
    -0.53
    ATES
    -0.52
    POSITIVE LOGITS
    nikov
    1.46
    chenko
    1.08
    tein
    1.03
    ofer
    1.01
    ti
    0.94
    tu
    0.94
    ima
    0.94
    adow
    0.92
    ield
    0.91
    ka
    0.91
    Activations Density 0.043%

    No Known Activations