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. 4-RES-JB
    6. 21049
    Prev
    Next
    INDEX
    Explanations

    mentions of notable persons with the suffix "-ous" in their name

    oai_token-act-pair · gpt-3.5-turbo

    words related to a specific suffix indicating quality or characteristic

    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
    ellen
    -0.79
    OWS
    -0.71
    NPR
    -0.70
    ruary
    -0.70
    é¾įå
    -0.69
    PsyNetMessage
    -0.68
    èª
    -0.68
    ARC
    -0.66
    STEP
    -0.65
    FN
    -0.65
    POSITIVE LOGITS
    Magikarp
    1.21
    ous
    1.05
    uit
    0.79
    ness
    0.78
    entials
    0.77
    soever
    0.77
    ivil
    0.75
    sa
    0.74
    gue
    0.74
    ity
    0.72
    Activations Density 0.021%

    No Known Activations