© 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. 0-RES-JB
    11. 13816
    Prev
    Next
    INDEX
    Explanations

    terms related to data storage capacity

    oai_token-act-pair · gpt-3.5-turbo

    terms related to data storage and measurement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Coll
    -0.75
     conj
    -0.67
     neutral
    -0.64
     ties
    -0.62
     Gun
    -0.61
     lod
    -0.61
     crossing
    -0.60
     hen
    -0.60
     Mus
    -0.60
     Fall
    -0.59
    POSITIVE LOGITS
    abyte
    3.88
    abytes
    3.77
    abit
    2.54
    apixel
    2.47
    awatts
    2.09
    adata
    1.32
    abase
    1.17
    cedented
    1.09
    ertodd
    1.07
    antically
    1.05
    Activations Density 0.019%

    No Known Activations