© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3-RES-JB
    11. 16892
    Prev
    Next
    INDEX
    Explanations

    references to a particular brand or company named "Fresh."

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the term "Fresh," particularly in the context of food services or brands

    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
    ietal
    -0.71
    orset
    -0.66
    orpor
    -0.65
    anco
    -0.63
    ooming
    -0.63
     controlled
    -0.62
    oscope
    -0.62
     dictate
    -0.62
    oulder
    -0.62
     annexed
    -0.62
    POSITIVE LOGITS
    water
    0.98
    Fresh
    0.98
    lings
    0.95
    bread
    0.92
    mans
    0.90
    ly
    0.82
    man
    0.82
    ness
    0.82
    lish
    0.79
    elight
    0.79
    Activations Density 0.009%

    No Known Activations