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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16775
    Prev
    Next
    INDEX
    Explanations

    phrases related to survival and events where people are surviving or being survivors

    oai_token-act-pair · gpt-3.5-turbo

    the term 'survivors' and its variants relating to people who have endured trauma or violence

    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
    lot
    -0.74
    /.
    -0.68
    asonic
    -0.68
    pin
    -0.67
    oshop
    -0.67
    undai
    -0.64
     Fancy
    -0.63
    frac
    -0.63
    )=(
    -0.63
    Dub
    -0.61
    POSITIVE LOGITS
     survivors
    3.82
     survivor
    3.05
     Survivors
    2.95
    surv
    2.01
    Surv
    1.90
     surviving
    1.89
     victims
    1.75
     Victims
    1.63
     Surv
    1.50
     Survivor
    1.47
    Activations Density 0.017%

    No Known Activations