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. 17694
    Prev
    Next
    INDEX
    Explanations

    nouns related to physical materials and textures

    oai_token-act-pair · gpt-3.5-turbo

    elements related to visual or aesthetic details

    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
    SEA
    -0.76
     citiz
    -0.69
     practition
    -0.68
    ufact
    -0.63
    SPA
    -0.62
    vironment
    -0.62
    ©¶æ¥µ
    -0.61
    SPONSORED
    -0.59
    ģĸ
    -0.59
    States
    -0.58
    POSITIVE LOGITS
     yarn
    0.63
    izont
    0.60
     beard
    0.60
    bones
    0.60
    Rot
    0.59
     mustache
    0.59
     toes
    0.58
     saline
    0.56
     brim
    0.55
     drown
    0.55
    Activations Density 1.578%

    No Known Activations