Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 3488
    Prev
    Next
    INDEX
    Explanations

    phrases or words indicating a sense of impending failure or negative outcomes

    oai_token-act-pair · gpt-3.5-turbo

    expressions of pessimism or fatalism, particularly the concept of being doomed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.75
    ATT
    -0.68
    overed
    -0.64
    TPP
    -0.64
    bara
    -0.64
    GS
    -0.64
    aque
    -0.63
    colo
    -0.62
    akers
    -0.62
    zanne
    -0.61
    POSITIVE LOGITS
     doomed
    1.12
     doom
    0.91
    icter
    0.84
     releg
    0.83
     challeng
    0.80
    itably
    0.79
     downfall
    0.78
     adolesc
    0.75
    iflower
    0.74
     desper
    0.73
    Activations Density 0.008%

    No Known Activations