© 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. 2-RES-JB
    11. 24200
    Prev
    Next
    INDEX
    Explanations

    descriptions or mentions of something being fresh

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "fresh" in various contexts

    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
    yip
    -0.71
    idget
    -0.66
    ipple
    -0.66
    ureau
    -0.65
    ittle
    -0.64
    afe
    -0.64
     Hobby
    -0.63
    owered
    -0.63
    ickson
    -0.62
    oried
    -0.62
    POSITIVE LOGITS
    ness
    0.97
    Fresh
    0.94
     fresh
    0.89
    foundland
    0.78
    lishes
    0.78
    lime
    0.77
    lish
    0.77
     fruits
    0.76
    é¾įåĸļ士
    0.72
    fresh
    0.72
    Activations Density 0.013%

    No Known Activations