© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1-RES-JB
    11. 14350
    Prev
    Next
    INDEX
    Explanations

    words related to negative outcomes or consequences

    oai_token-act-pair · gpt-3.5-turbo

    references to loss or its consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ENTS
    -0.70
     inventive
    -0.68
    ATT
    -0.66
    rouse
    -0.65
    ECK
    -0.63
     dotted
    -0.62
    thodox
    -0.62
    ":[{"
    -0.62
    ansky
    -0.61
     Occupations
    -0.61
    POSITIVE LOGITS
     loss
    1.11
     Loss
    1.06
    loss
    1.04
     aversion
    0.97
    iem
    0.89
     losses
    0.89
    byss
    0.82
     experien
    0.73
     landfall
    0.73
    luster
    0.72
    Activations Density 0.010%

    No Known Activations