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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 15790
    Prev
    Next
    INDEX
    Explanations

    text related to banners and other forms of advertisement or promotion

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "banner" and its variants

    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
    ulu
    -0.76
    OTOS
    -0.74
    urrency
    -0.72
    cephal
    -0.70
    nesota
    -0.67
    olation
    -0.64
    juries
    -0.64
    olated
    -0.64
    iott
    -0.63
    ivot
    -0.62
    POSITIVE LOGITS
     banners
    1.07
     banner
    1.05
    pole
    1.03
    boards
    0.82
     proclaiming
    0.82
    stones
    0.81
    holder
    0.79
    ram
    0.78
    board
    0.76
    holders
    0.76
    Activations Density 0.015%

    No Known Activations