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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 3990
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and equations within text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.68
    Serv
    -0.64
     realise
    -0.63
     disse
    -0.62
    ionics
    -0.60
     warns
    -0.60
     relieved
    -0.59
    2200
    -0.59
     realize
    -0.58
    ???
    -0.57
    POSITIVE LOGITS
    oret
    1.59
    atre
    1.30
    ories
    1.14
    ater
    1.14
    ory
    1.10
    resa
    1.09
    orem
    1.02
    odore
    0.96
    aters
    0.96
     fastest
    0.93
    Activations Density 0.081%

    No Known Activations