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. 21197
    Prev
    Next
    INDEX
    Explanations

    sentences ending with a full stop

    oai_token-act-pair · gpt-3.5-turbo

    sentences that indicate a score or outcome in a sports context

    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
     advis
    -0.93
     affili
    -0.85
     authorized
    -0.84
     coerc
    -0.83
     dissemination
    -0.81
     bindings
    -0.80
     censored
    -0.79
     regulators
    -0.79
     manuals
    -0.79
     commissions
    -0.77
    POSITIVE LOGITS
     Afterwards
    1.30
     However
    1.28
     Despite
    1.21
     With
    1.17
     Fans
    1.17
     Unfortunately
    1.16
     Having
    1.12
     Ahead
    1.11
     Meanwhile
    1.10
     Nevertheless
    1.08
    Activations Density 0.210%

    No Known Activations