© 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. 22136
    Prev
    Next
    INDEX
    Explanations

    obscure or less well-known terms or references within text

    oai_token-act-pair · gpt-3.5-turbo

    references to concepts and items that are considered obscure or hidden

    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
    hner
    -0.81
    Demand
    -0.75
    hao
    -0.71
    utherford
    -0.71
    ODUCT
    -0.68
    ourke
    -0.68
    ogh
    -0.66
    TD
    -0.65
    requency
    -0.64
    strength
    -0.64
    POSITIVE LOGITS
     obscure
    1.11
    uously
    0.84
     obscurity
    0.83
    ly
    0.74
     trivia
    0.73
    ulously
    0.72
    ously
    0.72
    ingly
    0.70
    ively
    0.70
     dece
    0.67
    Activations Density 0.007%

    No Known Activations