© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 861
    Prev
    Next
    INDEX
    Explanations

    prepositions such as "of"

    oai_token-act-pair · gpt-3.5-turbo

    the frequency and variation of the preposition "of" in different contexts

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

    No Comments

    Negative Logits
     preval
    -0.85
    zbollah
    -0.72
    respective
    -0.63
    inez
    -0.63
    fitting
    -0.61
     partName
    -0.61
    hao
    -0.60
     evaluations
    -0.60
    furt
    -0.60
    paren
    -0.60
    POSITIVE LOGITS
     sorts
    1.16
     fame
    0.72
     Brill
    0.70
     course
    0.69
    icial
    0.68
     epic
    0.65
     mankind
    0.64
     doom
    0.64
    ãĥīãĥ©ãĤ´ãĥ³
    0.64
     paradise
    0.64
    Activations Density 0.350%

    No Known Activations