© 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
    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. 14933
    Prev
    Next
    INDEX
    Explanations

    numeric values in an unusual notation

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols and abnormal characters in the text

    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
    NetMessage
    -0.89
    emouth
    -0.88
     hitch
    -0.83
    nect
    -0.81
    anooga
    -0.78
    istically
    -0.78
    fman
    -0.77
    mercial
    -0.76
    glers
    -0.75
    berra
    -0.75
    POSITIVE LOGITS
    ³
    0.95
    ת
    0.92
    Į
    0.91
    Ö¼
    0.89
    ——
    0.86
    ÙĨ
    0.86
    à¥
    0.84
    ²
    0.83
    ा
    0.82
    ÙĦ
    0.81
    Activations Density 0.005%

    No Known Activations