© 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. 4-RES-JB
    11. 24350
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and operations

    oai_token-act-pair · gpt-3.5-turbo

    structural elements of documentation or notation

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

    No Comments

    Negative Logits
    auna
    -0.77
    swers
    -0.74
    usage
    -0.61
     Citiz
    -0.60
    entimes
    -0.59
    elli
    -0.58
    osaurus
    -0.56
     endif
    -0.55
     intent
    -0.55
     faculty
    -0.55
    POSITIVE LOGITS
    PsyNetMessage
    0.80
    gged
    0.73
    udeau
    0.72
    ĪĴ
    0.68
    士
    0.68
    é»Ĵ
    0.68
    åº
    0.66
    éĹĺ
    0.65
    incinn
    0.64
    pload
    0.63
    Activations Density 0.762%

    No Known Activations