Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 10069
    Prev
    Next
    INDEX
    Explanations

    special characters within sentences like Ã, Ç, and "air quotes"

    oai_token-act-pair · gpt-3.5-turbo

    special characters or non-standard symbols

    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
    NetMessage
    -0.47
     mathemat
    -0.39
     Seym
    -0.37
    ĵĺ
    -0.35
     tradem
    -0.35
    enei
    -0.33
     Pwr
    -0.33
     vulner
    -0.32
     looph
    -0.31
    merce
    -0.31
    POSITIVE LOGITS
    iversary
    0.38
    lean
    0.38
    ividual
    0.36
    ues
    0.36
    lash
    0.35
    tenance
    0.34
    ãĥ³ãĤ¸
    0.34
    083
    0.34
    arius
    0.34
    cade
    0.34
    Activations Density 0.653%

    No Known Activations