© 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. 23761
    Prev
    Next
    INDEX
    Explanations

    names or words related to individuals named Kell**yan**

    oai_token-act-pair · gpt-3.5-turbo

    names, particularly those associated with specific individuals

    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
    share
    -0.84
    IBLE
    -0.80
    ðĿ
    -0.72
    REC
    -0.69
    UTERS
    -0.67
    bable
    -0.67
    Ms
    -0.66
    limit
    -0.65
    IVE
    -0.65
    Save
    -0.65
    POSITIVE LOGITS
    igans
    1.38
    kees
    1.17
    onymous
    1.06
    yan
    1.05
    athan
    0.97
    ous
    0.85
    thal
    0.85
    nan
    0.84
    igan
    0.84
    adan
    0.83
    Activations Density 0.005%

    No Known Activations