© 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. 4-RES-JB
    11. 13137
    Prev
    Next
    INDEX
    Explanations

    specific names, possibly of a person referred to as "Lind."

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named "Lind."

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

    No Comments

    Negative Logits
    OPLE
    -0.83
    CLASSIFIED
    -0.75
    Magikarp
    -0.73
    Ø©
    -0.69
    ABLE
    -0.66
    Dim
    -0.63
     FTA
    -0.63
     voc
    -0.61
     Samoa
    -0.61
    XM
    -0.59
    POSITIVE LOGITS
    gren
    1.15
    strom
    1.10
    isf
    1.07
    seys
    1.03
    enstein
    0.98
    quist
    0.95
    say
    0.94
    ahl
    0.94
    berg
    0.94
    holm
    0.94
    Activations Density 0.011%

    No Known Activations