© 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 EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 24294
    Prev
    Next
    INDEX
    Explanations

    acronyms and technical terms related to technology and telecommunications

    oai_token-act-pair · gpt-3.5-turbo

    technical acronyms and identifiers commonly used in data and computing contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    want
    -0.76
    folk
    -0.76
    taboola
    -0.70
    chester
    -0.69
    had
    -0.66
    best
    -0.64
     Oz
    -0.63
    amy
    -0.63
     Anthrop
    -0.63
    ande
    -0.62
    POSITIVE LOGITS
    s
    0.99
    Ds
    0.87
     compliant
    0.85
    +,
    0.84
    Os
    0.83
     holders
    0.83
     inhibitors
    0.81
    +.
    0.78
    OPS
    0.77
    Vs
    0.76
    Activations Density 0.231%

    No Known Activations