© 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. 7547
    Prev
    Next
    INDEX
    Explanations

    names or mentions of "Vlad" or "Glad" with various levels of importance, potentially for categorization or analysis

    oai_token-act-pair · gpt-3.5-turbo

    names and references to individuals, particularly those related to specific contexts or events

    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
    ELL
    -1.02
    EED
    -0.76
    ä¸Ń
    -0.74
    REE
    -0.73
     Countdown
    -0.68
    ModLoader
    -0.65
    lished
    -0.65
    natureconservancy
    -0.65
     compounded
    -0.64
     Bakr
    -0.64
    POSITIVE LOGITS
    imir
    1.40
    lad
    1.01
    mir
    0.97
    der
    0.94
    isl
    0.93
    ewater
    0.88
    imar
    0.80
    bach
    0.79
    ynam
    0.78
    osaurs
    0.77
    Activations Density 0.011%

    No Known Activations