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. 8837
    Prev
    Next
    INDEX
    Explanations

    locations or entities related to the color blue

    oai_token-act-pair · gpt-3.5-turbo

    references to the color blue or entities associated with the term "blue."

    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
    Ö¼
    -0.94
    ROR
    -0.84
    NRS
    -0.82
    uador
    -0.82
    rolet
    -0.78
     srfAttach
    -0.75
     IPM
    -0.74
    ITED
    -0.73
    IFA
    -0.73
    ernandez
    -0.73
    POSITIVE LOGITS
    prints
    1.35
    grass
    1.32
    berry
    1.17
    bird
    0.97
     ribbon
    0.95
    beard
    0.90
     Ribbon
    0.89
    berries
    0.88
    fin
    0.82
    irection
    0.82
    Activations Density 0.018%

    No Known Activations