© 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. 10505
    Prev
    Next
    INDEX
    Explanations

    programming-related terms such as file names and command line prompts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "pg" used in various contexts, likely referring to pages or programming elements

    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
     Bened
    -0.77
     Ic
    -0.73
    ufact
    -0.72
     thirds
    -0.70
    joined
    -0.67
     Despair
    -0.65
    fty
    -0.64
     Bie
    -0.63
    stru
    -0.61
    taboola
    -0.60
    POSITIVE LOGITS
    allery
    1.03
    insula
    0.95
    asus
    0.91
    sburg
    0.87
    eln
    0.85
    ression
    0.85
    PI
    0.85
    osate
    0.83
    sylvania
    0.82
    ENC
    0.82
    Activations Density 0.008%

    No Known Activations