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. 8-RES-JB
    6. 2898
    Prev
    Next
    INDEX
    Explanations

    terms related to geological or natural features, such as soil, sea, monsters, power, conservation, microbes, and intelligence

    oai_token-act-pair · gpt-3.5-turbo

    terms related to environmental issues and natural elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    nouns after adjectives

    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Misc

    No Comments

    Negative Logits
    ruary
    -0.78
    abase
    -0.77
    rentice
    -0.76
    ij士
    -0.71
    ãĤ¤ãĥĪ
    -0.70
    PDATE
    -0.69
    Reloaded
    -0.68
    trak
    -0.68
    oldemort
    -0.68
    ylan
    -0.68
    POSITIVE LOGITS
    hesion
    0.72
    icides
    0.68
    ifiers
    0.67
    natureconservancy
    0.67
    ioxide
    0.66
    ifier
    0.66
     Berman
    0.64
     IPM
    0.62
    ification
    0.58
    nels
    0.58
    Activations Density 0.705%

    No Known Activations