© 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. 2237
    Prev
    Next
    INDEX
    Explanations

    references to fans or fan-related content

    oai_token-act-pair · gpt-3.5-turbo

    mentions of fans and their reactions or engagement with a subject

    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
     Territ
    -0.61
    abus
    -0.61
     Osc
    -0.60
     Madness
    -0.60
     Surgery
    -0.59
    Govern
    -0.59
    tein
    -0.58
     Khe
    -0.57
     jarring
    -0.57
     perfect
    -0.56
    POSITIVE LOGITS
    atical
    1.02
    atics
    1.01
    haw
    1.01
    ubs
    0.95
    hip
    0.95
    atically
    0.93
    boys
    0.91
    erv
    0.89
    kies
    0.84
    hips
    0.80
    Activations Density 0.026%

    No Known Activations