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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 24388
    Prev
    Next
    INDEX
    Explanations

    sea creatures, specifically sea otters

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sea life and aquatic themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abase
    -0.85
    ãĤ¤ãĥĪ
    -0.76
    ij士
    -0.76
    trak
    -0.75
    ãĤ¶
    -0.73
    ãĤ§
    -0.71
    itely
    -0.71
    PDATE
    -0.70
    oldemort
    -0.69
    actionDate
    -0.67
    POSITIVE LOGITS
    amba
    0.64
     Islands
    0.62
    hesion
    0.61
     Emirates
    0.60
     runoff
    0.59
    ifications
    0.58
     dams
    0.57
     Cemetery
    0.56
     breat
    0.56
     haun
    0.55
    Activations Density 0.496%

    No Known Activations