© 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. 2-RES-JB
    11. 3945
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "geeks"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "geek" and its variants 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
    ãĥŁ
    -0.84
    OIL
    -0.74
     Veter
    -0.74
    Jordan
    -0.69
    oulos
    -0.69
    ENCE
    -0.68
    UCT
    -0.67
    icka
    -0.67
     Adin
    -0.66
    ãģĤ
    -0.64
    POSITIVE LOGITS
    bench
    1.08
    eeks
    1.06
     geek
    0.87
    haw
    0.83
     Geek
    0.82
    ery
    0.81
    Dad
    0.78
    arthed
    0.78
    core
    0.77
    EEK
    0.77
    Activations Density 0.008%

    No Known Activations