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. 2-RES-JB
    6. 10637
    Prev
    Next
    INDEX
    Explanations

    words related to the planet Earth or natural disasters like earthquakes

    oai_token-act-pair · gpt-3.5-turbo

    references to "Earth" and phenomena related to it, particularly earthquakes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acca
    -0.98
    ratulations
    -0.79
    aneers
    -0.75
    utations
    -0.75
    atta
    -0.72
    allery
    -0.72
     presumptive
    -0.71
    rations
    -0.70
    rators
    -0.68
    accompan
    -0.67
    POSITIVE LOGITS
    earth
    1.10
    lings
    0.92
    theless
    0.89
    worm
    0.86
    bolt
    0.84
    leigh
    0.83
    ly
    0.81
    shake
    0.79
    stone
    0.78
    oint
    0.77
    Activations Density 0.005%

    No Known Activations