© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1736
    Prev
    Next
    INDEX
    Explanations

    self-described or self-proclaimed individuals

    oai_token-act-pair · gpt-3.5-turbo

    phrases that identify individuals or groups by their self-descriptions

    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
    utton
    -0.65
    azaki
    -0.65
    adata
    -0.65
    akings
    -0.65
    è£ħ
    -0.65
    isons
    -0.63
    perature
    -0.62
    elight
    -0.61
    strings
    -0.61
     Simulator
    -0.61
    POSITIVE LOGITS
     adherent
    0.87
    sty
    0.85
    idable
    0.77
     member
    0.77
     believer
    0.73
     legislator
    0.72
     newcomer
    0.72
     gunman
    0.72
    proclaimed
    0.71
     dictator
    0.70
    Activations Density 0.060%

    No Known Activations