© 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. 18914
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions, decisions, and consequences

    oai_token-act-pair · gpt-3.5-turbo

    the presence of conjunctions, particularly "and," indicating connections or additions in the text

    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
    tnc
    -0.80
    ļéĨĴ
    -0.77
    Interested
    -0.75
    inent
    -0.74
    incial
    -0.71
    culus
    -0.70
    ANC
    -0.69
    Enlarge
    -0.69
    cerning
    -0.69
    rared
    -0.68
    POSITIVE LOGITS
     succeeded
    1.12
     deserve
    1.01
     rightly
    0.94
     reap
    0.93
     nobody
    0.90
     rightfully
    0.89
     waited
    0.87
     luckily
    0.87
     prevailed
    0.87
     rewarded
    0.86
    Activations Density 0.221%

    No Known Activations