© 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. 18631
    Prev
    Next
    INDEX
    Explanations

    names or references related to the name "Tam"

    oai_token-act-pair · gpt-3.5-turbo

    the proper noun "Tam" or variations of it, indicating a focus on this specific name in the context

    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
    «ĺ
    -0.65
    ģĸ
    -0.63
     uranium
    -0.60
     unaccompanied
    -0.59
    Ń·
    -0.59
    getic
    -0.59
    GROUND
    -0.58
    Ĥª
    -0.58
     precip
    -0.57
     semic
    -0.56
    POSITIVE LOGITS
    pering
    1.48
    pered
    1.29
    riel
    1.11
    ás
    1.08
    adra
    1.07
    many
    1.06
    iami
    1.06
    perty
    1.05
    arin
    1.04
    aki
    1.03
    Activations Density 0.032%

    No Known Activations