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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 19879
    Prev
    Next
    INDEX
    Explanations

    sentences ending with the punctuation mark "."

    oai_token-act-pair · gpt-3.5-turbo

    instances of sentences or statements

    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
     extinguished
    -0.79
     restraint
    -0.77
     overt
    -0.75
     extingu
    -0.75
     barric
    -0.71
     grip
    -0.71
     involuntary
    -0.70
     reflex
    -0.70
     sacked
    -0.69
     angle
    -0.69
    POSITIVE LOGITS
     Lastly
    1.64
     Additionally
    1.54
     Finally
    1.38
     Needless
    1.36
     Hopefully
    1.30
     Overall
    1.26
     Furthermore
    1.24
    Lastly
    1.22
     Unfortunately
    1.21
     Ultimately
    1.20
    Activations Density 0.512%

    No Known Activations