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. 3-RES-JB
    6. 10906
    Prev
    Next
    INDEX
    Explanations

    words related to a specific term "ister"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the suffix '-ister'

    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
    ¥µ
    -0.79
    ãĥ¼ãĥ³
    -0.70
    UTC
    -0.70
    ajo
    -0.65
     Kabul
    -0.65
    imester
    -0.64
    Score
    -0.63
    arcity
    -0.63
    ADRA
    -0.63
    ghazi
    -0.63
    POSITIVE LOGITS
    ial
    0.97
    loo
    0.94
    igans
    0.88
    iffe
    0.87
    ing
    0.84
    lies
    0.82
    nect
    0.77
    idge
    0.76
    zynski
    0.76
    hip
    0.75
    Activations Density 0.011%

    No Known Activations