© 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. 12721
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Al" and potentially phrases or terms related to him

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Al" in various contexts

    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
    intendent
    -0.93
    DragonMagazine
    -0.86
    ãĥ¼ãĥĨãĤ£
    -0.83
    enegger
    -0.79
     Chaser
    -0.77
    olicy
    -0.77
    manship
    -0.75
    éĹĺ
    -0.74
     Beware
    -0.72
     Nationwide
    -0.71
    POSITIVE LOGITS
    gebra
    1.13
    manac
    1.12
    ameda
    1.10
    addin
    0.99
     Jazeera
    0.99
    oha
    0.98
    gorith
    0.95
    ibaba
    0.95
    aska
    0.95
    umni
    0.94
    Activations Density 0.022%

    No Known Activations