© 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. 1-RES-JB
    11. 14396
    Prev
    Next
    INDEX
    Explanations

    phrases referring to a spatial or temporal midpoint

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "middle" in various contexts, particularly related to socioeconomic status or positioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SIGN
    -0.75
    gov
    -0.71
    etics
    -0.67
     Maxim
    -0.66
     Griffith
    -0.65
    utra
    -0.64
    orthy
    -0.63
    EH
    -0.62
    NVIDIA
    -0.61
    apo
    -0.60
    POSITIVE LOGITS
    middle
    1.09
     middle
    1.03
    uve
    0.85
     glove
    0.83
     mids
    0.78
    Middle
    0.72
    classes
    0.72
    idental
    0.72
    ogether
    0.70
    wich
    0.70
    Activations Density 0.011%

    No Known Activations