© 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. 10-RES-JB
    11. 2864
    Prev
    Next
    INDEX
    Explanations

    words related to personal relationships or individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to personal relationships or social dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SIM
    -0.62
    UCT
    -0.61
    sequ
    -0.60
     VIDEOS
    -0.58
    Module
    -0.57
    DX
    -0.57
    Integ
    -0.56
    rogens
    -0.56
    ilion
    -0.55
    ILLE
    -0.54
    POSITIVE LOGITS
     who
    1.85
     whom
    1.85
    who
    1.79
     whose
    1.44
    whose
    1.42
     Who
    1.08
    Who
    1.04
     fame
    0.97
    agher
    0.94
     wishing
    0.87
    Activations Density 0.900%

    No Known Activations