© 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. 15815
    Prev
    Next
    INDEX
    Explanations

    instances where the subject matter is being discussed in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific "subject" or topic throughout 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
     Zimmer
    -0.82
    IER
    -0.69
     Towers
    -0.67
     Andersen
    -0.67
     Kats
    -0.67
     fortune
    -0.66
    neau
    -0.65
    OURCE
    -0.65
    ereo
    -0.63
    éĹĺ
    -0.63
    POSITIVE LOGITS
    ivity
    1.11
    matter
    1.11
    ively
    1.05
    itatively
    0.97
    ivist
    0.94
    ivities
    0.92
    ivism
    0.91
     matter
    0.90
    iveness
    0.84
    topic
    0.84
    Activations Density 0.010%

    No Known Activations