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. 3-RES-JB
    6. 7519
    Prev
    Next
    INDEX
    Explanations

    terms related to fatigue or exhaustion

    oai_token-act-pair · gpt-3.5-turbo

    expressions of fatigue or exhaustion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    authorized
    -0.80
    izations
    -0.77
    iola
    -0.77
    byter
    -0.74
    vernment
    -0.70
    tein
    -0.67
    operated
    -0.65
    ection
    -0.65
     charism
    -0.64
    orthy
    -0.63
    POSITIVE LOGITS
    igue
    1.03
     tired
    0.89
    rums
    0.81
    åĭ
    0.74
     old
    0.73
    ness
    0.73
     clich
    0.69
     Archdemon
    0.67
    nesses
    0.67
     Colt
    0.66
    Activations Density 0.011%

    No Known Activations