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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3-RES-JB
    6. 19394
    Prev
    Next
    INDEX
    Explanations

    words related to people's names

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving the word "ling" in various contexts

    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
    raint
    -0.74
    schild
    -0.71
    ilion
    -0.69
    hemat
    -0.66
    raints
    -0.66
    quickShipAvailable
    -0.64
    udos
    -0.62
    illery
    -0.61
     respected
    -0.61
    emis
    -0.60
    POSITIVE LOGITS
    gling
    0.92
    tons
    0.89
    lass
    0.88
    phrine
    0.84
    HAM
    0.83
    ling
    0.82
    ham
    0.80
    ttes
    0.76
    dale
    0.75
    uez
    0.75
    Activations Density 0.015%

    No Known Activations