© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 11317
    Prev
    Next
    INDEX
    Explanations

    websites

    oai_token-act-pair · gpt-3.5-turbo

    references to websites with ".org" domains

    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
    Integer
    -0.67
     Nieto
    -0.63
    fts
    -0.62
     whiff
    -0.60
    faced
    -0.58
    ibus
    -0.58
     Proced
    -0.58
    Fine
    -0.57
    fixes
    -0.56
     Crate
    -0.56
    POSITIVE LOGITS
    enson
    1.07
    heim
    0.85
    istries
    0.83
    arin
    0.83
    allery
    0.82
    roup
    0.81
    orer
    0.79
    ensen
    0.76
    isf
    0.76
    lishes
    0.76
    Activations Density 0.005%

    No Known Activations