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. 8-RES-JB
    6. 14781
    Prev
    Next
    INDEX
    Explanations

    phrases related to having policies, procedures, or measures in place

    oai_token-act-pair · gpt-3.5-turbo

    references to established systems or structures in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etti
    -0.79
    jin
    -0.69
    anche
    -0.68
    yssey
    -0.67
    zzy
    -0.65
    otos
    -0.65
    anus
    -0.63
    gee
    -0.62
     Ging
    -0.61
    ourge
    -0.61
    POSITIVE LOGITS
    bos
    0.92
     whereby
    0.77
    alities
    0.74
     defences
    0.72
    holders
    0.68
     antioxid
    0.66
    atives
    0.66
     coping
    0.64
     protections
    0.63
     kitchens
    0.62
    Activations Density 0.027%

    No Known Activations