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. 23009
    Prev
    Next
    INDEX
    Explanations

    email-related content

    oai_token-act-pair · gpt-3.5-turbo

    incidents of invalid interactions or responses, often related to subscription errors or interruptions

    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
    ichick
    -0.72
    orer
    -0.67
    qs
    -0.67
    bd
    -0.65
    breakers
    -0.63
    opt
    -0.61
    draft
    -0.61
    kl
    -0.61
    Ó
    -0.61
    ãĥ¼ãĥĨãĤ£
    -0.61
    POSITIVE LOGITS
     IMAGES
    0.82
    PORT
    0.73
    BBC
    0.73
    LOS
    0.69
    GREEN
    0.67
    */(
    0.67
    LAB
    0.66
    Warning
    0.63
     presenter
    0.62
     guid
    0.62
    Activations Density 0.071%

    No Known Activations