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. 22432
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences that end with a strong punctuation mark

    oai_token-act-pair · gpt-3.5-turbo

    sentences that convey strong statements or conclusions

    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
     remaining
    -0.77
     allowance
    -0.76
     strict
    -0.74
     attrition
    -0.74
     rigorous
    -0.73
     continuous
    -0.72
     wet
    -0.72
     compliance
    -0.71
     tightening
    -0.70
     rigid
    -0.70
    POSITIVE LOGITS
     Called
    1.67
     Suppose
    1.21
     Specifically
    1.21
     Someone
    1.20
     Something
    1.17
     Somebody
    1.15
     Referred
    1.14
     It
    1.13
     Apparently
    1.10
     Named
    1.09
    Activations Density 0.392%

    No Known Activations