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. 0-RES-JB
    6. 11224
    Prev
    Next
    INDEX
    Explanations

    capitalized acronyms related to organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to the International Olympic Committee (IOC) and related 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
     land
    -0.68
     Alt
    -0.67
     lands
    -0.67
     christ
    -0.66
     rink
    -0.66
    urred
    -0.64
     deer
    -0.64
     Lands
    -0.64
     Land
    -0.62
     skin
    -0.62
    POSITIVE LOGITS
    IO
    4.35
    io
    2.29
    ios
    1.78
     IO
    1.58
    EO
    1.56
    IDA
    1.41
    IA
    1.39
    ION
    1.25
     io
    1.22
    iov
    1.22
    Activations Density 0.008%

    No Known Activations