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. 8-RES-JB
    6. 12147
    Prev
    Next
    INDEX
    Explanations

    sentences that don't have a clear pattern or theme, containing a mix of words that don't seem to have a cohesive topic

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation and expressions of understanding or acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ŃĶ
    -0.78
    ãĥĹ
    -0.72
     indistinguishable
    -0.69
    ãĥ©ãĥ³
    -0.67
    oho
    -0.66
     accuser
    -0.64
     identical
    -0.60
     herald
    -0.59
     ante
    -0.59
     endorsed
    -0.58
    POSITIVE LOGITS
     Luckily
    1.84
     Fortunately
    1.73
     Thankfully
    1.66
     Nevertheless
    1.49
    Luckily
    1.49
     Worse
    1.48
     Nonetheless
    1.44
     Therefore
    1.43
    Fortunately
    1.40
     Consequently
    1.39
    Activations Density 0.854%

    No Known Activations