© 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. 1-RES-JB
    11. 24007
    Prev
    Next
    INDEX
    Explanations

    names related to a person named "Linden"

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the name "Lind."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OPLE
    -0.88
    ably
    -0.72
    Rated
    -0.72
     constitu
    -0.72
    CLASSIFIED
    -0.71
    Magikarp
    -0.70
    Downloadha
    -0.68
    ABLE
    -0.67
     voc
    -0.64
    ãĥĩ
    -0.63
    POSITIVE LOGITS
    gren
    1.12
    strom
    1.07
     Lind
    0.99
    seys
    0.97
    enstein
    0.97
    ahl
    0.94
    quist
    0.93
    hurst
    0.93
    isf
    0.92
    gaard
    0.91
    Activations Density 0.006%

    No Known Activations