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. 10-RES-JB
    6. 18018
    Prev
    Next
    INDEX
    Explanations

    phrases related to social progress and the functioning of society

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to societal challenges and the importance of collective action for change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     assorted
    -0.74
    catentry
    -0.73
     Blades
    -0.61
     nods
    -0.61
    alis
    -0.60
     respectively
    -0.59
     Bits
    -0.59
     considerable
    -0.59
     various
    -0.58
     periodically
    -0.57
    POSITIVE LOGITS
     anymore
    1.50
     unless
    1.39
     without
    1.24
    unless
    1.17
     nor
    1.15
     WITHOUT
    1.12
    without
    1.10
     indefinitely
    0.94
     Without
    0.92
     except
    0.89
    Activations Density 0.570%

    No Known Activations