© 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. 3-RES-JB
    11. 21044
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical errors and instructions

    oai_token-act-pair · gpt-3.5-turbo

    box office revenue figures associated with movies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Enlarge
    -0.34
    uchin
    -0.33
    icago
    -0.33
    =-=-
    -0.31
    istries
    -0.30
     âĢķ
    -0.30
    Fast
    -0.29
    ornia
    -0.29
    esi
    -0.28
    -0.28
    POSITIVE LOGITS
    theless
    0.37
     comprom
    0.33
     planners
    0.28
    ITNESS
    0.28
     Coffin
    0.28
    hiba
    0.27
    ONSORED
    0.27
     Oliv
    0.27
     inclination
    0.27
    airo
    0.25
    Activations Density 8.182%

    No Known Activations