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. 8660
    Prev
    Next
    INDEX
    Explanations

    medical or anatomical terms, particularly related to fractures and body parts, focusing especially on the femur

    oai_token-act-pair · gpt-3.5-turbo

    terms related to femininity or female attributes

    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
     Shinra
    -0.71
     Oaks
    -0.68
     Carbuncle
    -0.67
     Yose
    -0.66
     guiActiveUnfocused
    -0.65
    BuyableInstoreAndOnline
    -0.64
    ively
    -0.63
     Monarch
    -0.62
     Amen
    -0.62
     Bentley
    -0.61
    POSITIVE LOGITS
    puter
    0.98
    rite
    0.94
    inity
    0.93
    ldom
    0.91
    ili
    0.87
    ilit
    0.87
    orp
    0.85
    uer
    0.84
    bots
    0.82
    pire
    0.82
    Activations Density 0.031%

    No Known Activations