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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7-RES-JB
    6. 1377
    Prev
    Next
    INDEX
    Explanations

    punctuation marks at the end of a sentence

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation, specifically periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     calendar
    -0.70
     transact
    -0.69
     cradle
    -0.67
     bargain
    -0.67
     stalking
    -0.66
     bite
    -0.66
     opportunity
    -0.66
     fleeing
    -0.66
     ogre
    -0.65
     enrich
    -0.65
    POSITIVE LOGITS
     Flavoring
    1.04
    henko
    0.90
    psc
    0.85
     Architects
    0.84
     Shots
    0.82
     Associates
    0.81
     Conversely
    0.79
     Exactly
    0.78
     Doors
    0.78
     Supported
    0.78
    Activations Density 0.120%

    No Known Activations