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. 9-RES-JB
    6. 6209
    Prev
    Next
    INDEX
    Explanations

    statements related to ideological or philosophical concepts, particularly individualism and consciousness

    oai_token-act-pair · gpt-3.5-turbo

    statements primarily involving the concept of "being" or "existence."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addons
    -0.78
    ppa
    -0.73
    usercontent
    -0.72
     congr
    -0.71
    poke
    -0.70
    Hey
    -0.69
     throats
    -0.68
    IFA
    -0.67
    IDs
    -0.67
    boarding
    -0.66
    POSITIVE LOGITS
     analogous
    1.14
     insepar
    1.12
     contrasted
    1.06
     therefore
    1.04
     intimately
    1.04
     embodied
    1.02
     principally
    1.01
     chiefly
    1.01
     manifested
    1.01
     characterized
    1.00
    Activations Density 0.474%

    No Known Activations