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. 8-RES-JB
    6. 16044
    Prev
    Next
    INDEX
    Explanations

    adjectives related to prestigious institutions or people

    oai_token-act-pair · gpt-3.5-turbo

    words with specific suffixes or endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Not in Any Lists

    No Comments

    Negative Logits
    BILITIES
    -1.09
    BILITY
    -0.77
    vironment
    -0.67
     unfocusedRange
    -0.63
    SpaceEngineers
    -0.61
    FontSize
    -0.61
     Tos
    -0.60
     sugg
    -0.60
    Http
    -0.59
    ĻĤ
    -0.59
    POSITIVE LOGITS
    schild
    0.71
    iday
    0.71
    arson
    0.70
    ouk
    0.67
    igans
    0.67
    nir
    0.66
    ueller
    0.66
    amines
    0.66
    api
    0.64
    urat
    0.63
    Activations Density 0.200%

    No Known Activations