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. 14389
    Prev
    Next
    INDEX
    Explanations

    numerical values indicating an amount of money

    oai_token-act-pair · gpt-3.5-turbo

    amounts of money or numerical values in a financial context

    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
    sterdam
    -0.87
    ulhu
    -0.74
    actic
    -0.73
    roit
    -0.70
    argo
    -0.69
    omen
    -0.69
    aken
    -0.69
    sein
    -0.67
    rina
    -0.67
    reon
    -0.66
    POSITIVE LOGITS
    interstitial
    0.93
    essed
    0.89
    esses
    0.79
    cffff
    0.73
    lbs
    0.71
     lashes
    0.71
    pees
    0.71
    288
    0.70
    DOS
    0.68
    ess
    0.65
    Activations Density 0.030%

    No Known Activations