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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6882
    Prev
    Next
    INDEX
    Explanations

    phrases related to close relationships

    oai_token-act-pair · gpt-3.5-turbo

    suffixes indicative of relationships or states of being

    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
    imil
    -0.78
    dinand
    -0.71
    Mos
    -0.67
    bang
    -0.65
    ENN
    -0.63
    itect
    -0.61
    ãĤ¤
    -0.61
    mbuds
    -0.61
    amar
    -0.60
    IFIC
    -0.60
    POSITIVE LOGITS
    lihood
    0.77
    hire
    0.72
    âĶĢ
    0.72
    ttes
    0.71
    ially
    0.70
     Gaw
    0.69
    oute
    0.65
    ername
    0.64
    âĶĢâĶĢ
    0.62
    ught
    0.62
    Activations Density 0.599%

    No Known Activations