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

    Neuronpedia

    APICircuit 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. 7895
    Prev
    Next
    INDEX
    Explanations

    terms related to preservation and restoration of heritage or historical items

    oai_token-act-pair · gpt-3.5-turbo

    terms related to preservation and restoration efforts

    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
    liam
    -0.80
    ells
    -0.79
    gs
    -0.74
    eva
    -0.73
    tiny
    -0.71
    ched
    -0.69
    olls
    -0.68
    ones
    -0.68
    roc
    -0.68
    atu
    -0.67
    POSITIVE LOGITS
     restoration
    0.93
     buffs
    0.89
     Restoration
    0.87
     preservation
    0.87
    ist
    0.83
    ists
    0.82
     efforts
    0.81
    ism
    0.80
     derby
    0.79
    icultural
    0.76
    Activations Density 0.023%

    No Known Activations