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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 23290
    Prev
    Next
    INDEX
    Explanations

    the text "ussie" with a varying intensity based on the context

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific term or name related to Australian culture

    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
     rud
    -0.79
     IPM
    -0.71
     Mysteries
    -0.65
     Rohing
    -0.65
     agric
    -0.65
     pag
    -0.64
    ×Ļ×
    -0.64
    Hor
    -0.63
     Aram
    -0.63
    mone
    -0.63
    POSITIVE LOGITS
    eson
    2.08
    irc
    1.82
    ussie
    1.75
     Thing
    1.31
    orean
    1.26
     Commander
    1.21
     Norris
    1.09
    iverse
    1.08
    ilde
    1.03
    argo
    1.02
    Activations Density 0.042%

    No Known Activations