© 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. 0-RES-JB
    11. 8164
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of resolve or determination

    oai_token-act-pair · gpt-3.5-turbo

    words related to recovery or restoration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    loo
    -0.90
     Spiral
    -0.73
    behind
    -0.72
    speak
    -0.69
     Digest
    -0.68
     Bentley
    -0.68
    odiac
    -0.67
    LLOW
    -0.67
    aldi
    -0.66
    evil
    -0.65
    POSITIVE LOGITS
     res
    3.74
     Res
    1.58
    Res
    1.52
    res
    1.35
     resize
    1.30
     RES
    1.27
     resettlement
    1.26
    RES
    1.20
     rese
    1.17
     rel
    1.16
    Activations Density 0.020%

    No Known Activations