Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 14646
    Prev
    Next
    INDEX
    Explanations

    sentences that end with a full stop

    oai_token-act-pair · gpt-3.5-turbo

    sentence terminators, particularly periods

    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
     quir
    -0.93
     shorthand
    -0.79
     prud
    -0.79
     elusive
    -0.79
     unrem
    -0.76
     langu
    -0.75
     enriched
    -0.74
    —"
    -0.74
     twent
    -0.74
     disemb
    -0.73
    POSITIVE LOGITS
     Whilst
    1.70
     Therefore
    1.56
     Additionally
    1.54
     Lastly
    1.51
     However
    1.47
     Needless
    1.40
     Furthermore
    1.39
     Unfortunately
    1.38
     Lets
    1.36
     Secondly
    1.35
    Activations Density 0.917%

    No Known Activations