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. 1-RES-JB
    6. 13589
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Fresh" along with other words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    the repeated mention of the term "Fresh" in relation to a specific television series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ietal
    -0.67
     respecting
    -0.64
    orset
    -0.63
    XXXX
    -0.62
     furiously
    -0.62
     abused
    -0.60
     operated
    -0.60
     controlled
    -0.60
    ooming
    -0.60
    anco
    -0.60
    POSITIVE LOGITS
    Fresh
    1.09
     Fresh
    0.96
    bread
    0.91
    ness
    0.87
    isbury
    0.86
    lings
    0.86
    water
    0.83
    fresh
    0.82
    grass
    0.81
    lic
    0.79
    Activations Density 0.006%

    No Known Activations