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. 19094
    Prev
    Next
    INDEX
    Explanations

    words related to actions or commands such as 'backing', 'tracked', 'kicking', 'ducks'

    oai_token-act-pair · gpt-3.5-turbo

    words related to debt and financial obligations

    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
    enegger
    -0.78
    EVA
    -0.70
    issance
    -0.69
     Trance
    -0.68
     TODAY
    -0.67
    imov
    -0.65
    enment
    -0.64
    ITED
    -0.64
    endez
    -0.62
    oir
    -0.62
    POSITIVE LOGITS
    oshenko
    0.99
    edo
    0.86
    bones
    0.85
     torches
    0.84
    bits
    0.79
    uyomi
    0.78
    bon
    0.73
    pointers
    0.71
    boxes
    0.71
    pole
    0.70
    Activations Density 0.061%

    No Known Activations