© 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. 12265
    Prev
    Next
    INDEX
    Explanations

    keywords related to the chemical compound 'atin' or the abbreviation 'cin'

    oai_token-act-pair · gpt-3.5-turbo

    suffixes related to chemical compounds and terminology

    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
    atum
    -0.91
    ãĥł
    -0.89
    ACTED
    -0.71
    è»
    -0.68
     Myster
    -0.65
    Task
    -0.65
     bombshell
    -0.64
    ãĥĥãĥī
    -0.62
    RES
    -0.62
     Curt
    -0.62
    POSITIVE LOGITS
    atin
    4.03
    cin
    1.82
    elin
    1.50
    ulin
    1.43
    oin
    1.30
    okin
    1.28
    illin
    1.25
    asin
    1.24
    tin
    1.19
    agin
    1.18
    Activations Density 0.019%

    No Known Activations