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

    Neuronpedia

    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. 1-RES-JB
    11. 22902
    Prev
    Next
    INDEX
    Explanations

    words related to online services or platforms

    oai_token-act-pair · gpt-3.5-turbo

    specific cultural references or terms from media and entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cryst
    -0.73
     princ
    -0.70
     nutrit
    -0.70
     qualitative
    -0.69
     BIT
    -0.69
     harmonic
    -0.68
     proport
    -0.68
     separation
    -0.67
     Plant
    -0.66
     finer
    -0.66
    POSITIVE LOGITS
    lov
    1.00
    ãĤ¹ãĥĪ
    0.92
    etsk
    0.91
    sty
    0.88
    soon
    0.88
    hus
    0.88
    ument
    0.87
    antes
    0.87
    vg
    0.84
    rn
    0.83
    Activations Density 0.036%

    No Known Activations