© 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. 3635
    Prev
    Next
    INDEX
    Explanations

    terms related to Scientology

    oai_token-act-pair · gpt-3.5-turbo

    references to the Church of Scientology

    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
     Fir
    -0.76
    hower
    -0.74
     Higgins
    -0.73
     Gaw
    -0.72
     Ashe
    -0.71
    theless
    -0.69
     Mulcair
    -0.68
    tips
    -0.68
     Blow
    -0.68
     Ryder
    -0.67
    POSITIVE LOGITS
    onte
    0.83
     Scientology
    0.81
     Scient
    0.81
    ophile
    0.74
    Leaks
    0.74
    inct
    0.74
    estial
    0.73
    uthor
    0.72
    hess
    0.72
     Celebrity
    0.72
    Activations Density 0.013%

    No Known Activations