© 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. 2-RES-JB
    11. 5439
    Prev
    Next
    INDEX
    Explanations

    names and terms possibly related to people's names

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals or entities, particularly those with unusual or culturally specific names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UTION
    -0.81
    ERSON
    -0.80
    姫
    -0.79
    ISTER
    -0.74
    çīĪ
    -0.74
    OTH
    -0.72
    ORN
    -0.71
    erella
    -0.70
    Ö¼
    -0.70
    989
    -0.69
    POSITIVE LOGITS
     Nou
    1.11
    medi
    0.88
     citiz
    0.86
     unden
    0.85
     traged
    0.85
    vell
    0.82
    mers
    0.81
    rily
    0.81
    lette
    0.80
     unpre
    0.78
    Activations Density 0.006%

    No Known Activations