© 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. 3-RES-JB
    11. 13644
    Prev
    Next
    INDEX
    Explanations

    composers

    oai_token-act-pair · gpt-3.5-turbo

    mentions of composers and compositions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    naire
    -0.89
    naires
    -0.75
    payer
    -0.71
     Alibaba
    -0.69
     Mong
    -0.66
    ħĭ
    -0.65
     Breed
    -0.64
     Eag
    -0.62
     Len
    -0.62
     LM
    -0.62
    POSITIVE LOGITS
    itional
    0.91
     compos
    0.83
    itors
    0.82
    ensation
    0.81
    veyard
    0.79
     subsequ
    0.77
     misunder
    0.76
    itor
    0.74
    itals
    0.74
    xual
    0.73
    Activations Density 0.026%

    No Known Activations