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

    Neuronpedia

    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. 22301
    Prev
    Next
    INDEX
    Explanations

    mentions of a character named "Mondo"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific character or entity

    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
    TY
    -0.85
    jriwal
    -0.82
    ttle
    -0.77
    mented
    -0.75
    ty
    -0.73
    TPS
    -0.67
    tty
    -0.65
    TOP
    -0.65
     cumbers
    -0.64
    ulators
    -0.63
    POSITIVE LOGITS
    ondo
    0.83
    SourceFile
    0.69
    claimer
    0.69
    zzo
    0.68
    ose
    0.68
    vernment
    0.65
    ivari
    0.64
    issance
    0.63
    opsis
    0.62
     latt
    0.61
    Activations Density 0.014%

    No Known Activations