© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 6521
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Tur" with varying activation levels

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific term related to a popular gaming franchise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     largeDownload
    -0.79
     [&
    -0.78
    ãģ®éŃĶ
    -0.73
    Constructed
    -0.71
     Cruel
    -0.71
    ablishment
    -0.71
    ãģį
    -0.69
    IZE
    -0.68
     ECO
    -0.67
     Known
    -0.67
    POSITIVE LOGITS
    fing
    1.16
    bul
    1.12
    lette
    1.11
    moil
    1.05
    geon
    1.02
    rigan
    1.00
    rible
    0.99
    anche
    0.99
    ban
    0.96
    kish
    0.95
    Activations Density 0.007%

    No Known Activations