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. 11822
    Prev
    Next
    INDEX
    Explanations

    words related to scientific concepts, particularly those related to inorganic and organic matter

    oai_token-act-pair · gpt-3.5-turbo

    scientific terms related to organic materials and their properties

    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
     Ct
    -0.71
    accompan
    -0.66
    pid
    -0.66
    camp
    -0.63
    Austin
    -0.61
    Ct
    -0.60
    TX
    -0.58
     Hod
    -0.57
    utor
    -0.57
     lit
    -0.56
    POSITIVE LOGITS
    urities
    0.74
     Journals
    0.72
    iencies
    0.71
    sembly
    0.71
    ilus
    0.68
    iliary
    0.67
    aurus
    0.66
    imeters
    0.66
    wered
    0.65
    pedia
    0.65
    Activations Density 0.119%

    No Known Activations