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. 0-RES-JB
    6. 3963
    Prev
    Next
    INDEX
    Explanations

    words related to chemical elements or compounds

    oai_token-act-pair · gpt-3.5-turbo

    words related to chemical and scientific terminologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mornings
    -0.65
     unaccount
    -0.59
     RIS
    -0.58
     guaranteed
    -0.57
     GOODMAN
    -0.56
     Millions
    -0.54
     spaced
    -0.54
     stalk
    -0.54
    WD
    -0.53
     poaching
    -0.53
    POSITIVE LOGITS
    ic
    4.05
    ics
    2.32
    icism
    2.04
    IC
    1.94
    icist
    1.93
    ici
    1.93
    icc
    1.88
    icity
    1.86
    ically
    1.68
    icular
    1.63
    Activations Density 0.035%

    No Known Activations