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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 15286
    Prev
    Next
    INDEX
    Explanations

    proper names (often related to famous individuals) or keywords such as "recipe", "cafe", "performance", and "horror film"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of certain names and terms, particularly those related to Australian culture or 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
    lehem
    -0.72
     fines
    -0.71
     grandchildren
    -0.63
    aez
    -0.62
     setbacks
    -0.62
    cause
    -0.62
    ibles
    -0.60
    rosso
    -0.60
     acute
    -0.60
    uously
    -0.59
    POSITIVE LOGITS
    velt
    0.99
     Rampage
    0.78
    heid
    0.77
     Janeiro
    0.74
    lund
    0.70
    kefeller
    0.68
    estern
    0.68
    Unix
    0.68
    restling
    0.66
    phant
    0.65
    Activations Density 0.128%

    No Known Activations