© 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. 5512
    Prev
    Next
    INDEX
    Explanations

    references to the name "Ramsey"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly those with the last name "Ramsey" or similar variations

    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
    76561
    -0.76
    aucas
    -0.74
    ensed
    -0.69
    berman
    -0.68
    rees
    -0.64
    ensing
    -0.64
    ensable
    -0.63
    reek
    -0.62
    aren
    -0.61
     Samar
    -0.58
    POSITIVE LOGITS
     Ramsey
    1.08
    irez
    0.94
    ©¶æ¥µ
    0.86
    gaard
    0.80
    ette
    0.79
    ÃŃa
    0.74
     lapt
    0.73
    seys
    0.72
    hyde
    0.72
    grain
    0.71
    Activations Density 0.005%

    No Known Activations