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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-RES-JB
    6. 3517
    Prev
    Next
    INDEX
    Explanations

    words related to feeling fed up or frustrated with a situation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "fed" indicating the feeding or provision of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istically
    -0.74
    isms
    -0.73
     Ashes
    -0.62
    istic
    -0.60
    ities
    -0.58
     Goo
    -0.58
     Device
    -0.57
     Difference
    -0.57
     Quarterly
    -0.57
     Templar
    -0.56
    POSITIVE LOGITS
    oras
    1.28
    ora
    1.23
    Fed
    0.95
    rique
    0.94
    ric
    0.91
    elsen
    0.88
    rix
    0.86
    fed
    0.85
    ¡
    0.84
    ression
    0.84
    Activations Density 0.007%

    No Known Activations