© 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. 3-RES-JB
    11. 15055
    Prev
    Next
    INDEX
    Explanations

    names, specifically the name "Ernest"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly those named Ernest or Tol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rivals
    -0.70
    gpu
    -0.67
    Ħ¢
    -0.66
    hesda
    -0.63
    busters
    -0.62
    DAQ
    -0.61
    peak
    -0.60
    webkit
    -0.59
    rals
    -0.58
     finance
    -0.57
    POSITIVE LOGITS
    uing
    0.88
    isted
    0.86
    ined
    0.83
    ories
    0.82
    ibrary
    0.78
    olon
    0.78
    ueless
    0.77
    uably
    0.75
    orio
    0.75
     Sylvia
    0.75
    Activations Density 0.027%

    No Known Activations