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. 22470
    Prev
    Next
    INDEX
    Explanations

    phrases related to establishing or founding something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the establishment or creation of something

    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
    obi
    -0.65
    Magn
    -0.62
     Bulg
    -0.62
     Russo
    -0.59
    gee
    -0.58
    onso
    -0.58
    Brow
    -0.58
     Fortune
    -0.57
     pierced
    -0.57
     Jae
    -0.57
    POSITIVE LOGITS
    river
    0.87
    dates
    0.82
    olicy
    0.78
     tents
    0.76
    REAM
    0.69
    ezvous
    0.66
    dule
    0.66
    nect
    0.65
    acebook
    0.64
     upd
    0.63
    Activations Density 0.039%

    No Known Activations