© 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. 3-RES-JB
    11. 5882
    Prev
    Next
    INDEX
    Explanations

    words related to a specific surname "Baker"

    oai_token-act-pair · gpt-3.5-turbo

    a last name or surname

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Detention
    -0.60
     vicinity
    -0.59
     pall
    -0.59
     FEC
    -0.57
    ascar
    -0.56
     seriousness
    -0.55
    sent
    -0.55
    hovah
    -0.54
     diverse
    -0.54
    itars
    -0.53
    POSITIVE LOGITS
    loo
    1.33
    idge
    0.83
    arta
    0.82
    itus
    0.80
    jee
    0.79
    aker
    0.78
     extraord
    0.77
    iffe
    0.77
    iffs
    0.76
    oms
    0.75
    Activations Density 0.009%

    No Known Activations