© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 16361
    Prev
    Next
    INDEX
    Explanations

    phrases that mention a specific individual's name paired with a profession or title

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and significant terms related to notable individuals and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sembly
    -0.82
    ©¶æ¥µ
    -0.82
    ucha
    -0.82
     Hik
    -0.82
     Taj
    -0.81
    uana
    -0.79
    anto
    -0.79
    emis
    -0.77
    imei
    -0.75
    agy
    -0.74
    POSITIVE LOGITS
     Bl
    2.57
    Bl
    2.20
     BL
    2.02
    bl
    1.97
     bl
    1.76
    BL
    1.64
     blob
    1.49
     Blanc
    1.42
     Blair
    1.34
     Blaz
    1.28
    Activations Density 0.157%

    No Known Activations