© 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 EvalsExportsAPI 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. 12625
    Prev
    Next
    INDEX
    Explanations

    references to negative feelings or actions towards something

    oai_token-act-pair · gpt-3.5-turbo

    expressions of disdain or negativity

    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
     Maduro
    -0.78
     confir
    -0.68
     Herrera
    -0.67
     Romero
    -0.67
    ural
    -0.66
    ÃįÃį
    -0.64
     Fine
    -0.64
    uers
    -0.64
     Trend
    -0.62
     Bland
    -0.62
    POSITIVE LOGITS
     401
    1.52
     hated
    1.32
     tid
    1.30
    atche
    1.21
     disguise
    1.11
     penn
    1.10
     Tid
    1.09
    din
    1.07
     Schr
    1.02
     disguised
    1.00
    Activations Density 0.050%

    No Known Activations