© 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. 8-RES-JB
    11. 8351
    Prev
    Next
    INDEX
    Explanations

    phrases related to shared experiences or activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "together."

    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
    cock
    -0.67
    Fed
    -0.64
    anty
    -0.62
    arthed
    -0.61
    unc
    -0.59
    ysis
    -0.57
    ako
    -0.57
    ãĥ©ãĥ³
    -0.56
    ollar
    -0.56
    ream
    -0.56
    POSITIVE LOGITS
    ieth
    0.77
    standing
    0.68
     with
    0.67
    ness
    0.66
    with
    0.65
     wi
    0.63
    eous
    0.63
    !.
    0.63
    heid
    0.62
     Respect
    0.62
    Activations Density 0.035%

    No Known Activations