© 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. 455
    Prev
    Next
    INDEX
    Explanations

    terms related to mediation and mediators

    oai_token-act-pair · gpt-3.5-turbo

    terms related to mediation and mediators in various contexts

    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
    âĢ¢âĢ¢
    -0.90
    Leary
    -0.73
    IELD
    -0.73
    âķIJ
    -0.72
    BOOK
    -0.70
    âķIJâķIJ
    -0.70
    print
    -0.69
     Dusk
    -0.67
    TOP
    -0.67
    âĻ¦
    -0.67
    POSITIVE LOGITS
     medi
    1.33
    ocr
    1.01
    medi
    0.96
    emate
    0.85
     mediation
    0.82
    ocular
    0.77
    icum
    0.76
    iator
    0.74
    oti
    0.74
    ator
    0.74
    Activations Density 0.006%

    No Known Activations