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. 3-RES-JB
    6. 14201
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "skull"

    oai_token-act-pair · gpt-3.5-turbo

    references to skulls and related imagery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Published
    -0.82
    agonist
    -0.69
    bidden
    -0.67
    zona
    -0.67
     NCT
    -0.66
    EX
    -0.65
    20439
    -0.65
     Supporters
    -0.64
    Avg
    -0.63
    ARY
    -0.63
    POSITIVE LOGITS
     skull
    1.20
     skulls
    1.04
    bones
    1.00
    bone
    0.93
     bones
    0.91
     fracture
    0.82
    caps
    0.82
    Bone
    0.80
     fractures
    0.78
    cap
    0.74
    Activations Density 0.008%

    No Known Activations