© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 9544
    Prev
    Next
    INDEX
    Explanations

    references to specific organizations or entities with the acronym "HS"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific organization or institution identified by "HS"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nesota
    -0.71
    fman
    -0.69
    bidden
    -0.68
     Samoa
    -0.67
     Tribunal
    -0.63
    runtime
    -0.61
    osi
    -0.61
    verages
    -0.61
    circle
    -0.61
    taboola
    -0.61
    POSITIVE LOGITS
    HS
    1.36
    Ds
    1.01
    IFT
    0.93
    OOL
    0.92
    HT
    0.92
    ocial
    0.90
    IL
    0.88
    YS
    0.88
    ospital
    0.87
    ustain
    0.87
    Activations Density 0.007%

    No Known Activations