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. 0-RES-JB
    6. 3475
    Prev
    Next
    INDEX
    Explanations

    references to computer servers

    oai_token-act-pair · gpt-3.5-turbo

    references to servers in the context of technology and computing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bagg
    -0.74
     Barg
    -0.67
    eco
    -0.65
     Floyd
    -0.64
    imar
    -0.64
    odor
    -0.64
     Calvin
    -0.63
    allic
    -0.63
    ament
    -0.63
     Elliott
    -0.63
    POSITIVE LOGITS
     server
    3.51
     servers
    2.86
     Server
    2.61
    server
    2.31
    Server
    2.29
    erver
    1.66
     client
    1.58
    client
    1.42
    Client
    1.36
     Client
    1.35
    Activations Density 0.020%

    No Known Activations