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. 7-RES-JB
    6. 8141
    Prev
    Next
    INDEX
    Explanations

    medical terms and conditions

    oai_token-act-pair · gpt-3.5-turbo

    key concepts related to evidence or underlying arguments in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )"
    -0.61
     )]
    -0.58
     violates
    -0.57
    )\
    -0.55
    "],"
    -0.55
    })
    -0.54
    )]
    -0.54
    emies
    -0.54
    ebook
    -0.52
    },"
    -0.50
    POSITIVE LOGITS
    vertisement
    0.62
    interstitial
    0.54
     tremend
    0.51
     Pew
    0.51
    ozy
    0.49
    ukong
    0.47
    awaru
    0.46
    yout
    0.46
    *:
    0.45
    wrapper
    0.45
    Activations Density 1.319%

    No Known Activations