© 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. 4-RES-JB
    11. 17082
    Prev
    Next
    INDEX
    Explanations

    terms related to identifying specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals, denoted by the term "person."

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

    No Comments

    Negative Logits
     Lans
    -0.72
    enthal
    -0.72
     Lank
    -0.68
    unctions
    -0.66
    CCC
    -0.65
    DL
    -0.63
    NP
    -0.63
    Tx
    -0.63
     Lions
    -0.63
     corridors
    -0.62
    POSITIVE LOGITS
    hood
    1.27
    nel
    1.02
    acles
    0.83
     who
    0.81
    ification
    0.79
    ified
    0.78
    nels
    0.78
    uscript
    0.77
    ifies
    0.76
    who
    0.76
    Activations Density 0.037%

    No Known Activations