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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7-RES-JB
    6. 7164
    Prev
    Next
    INDEX
    Explanations

    sentences that end with strong punctuation marks (like exclamation marks or periods)

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with punctuation marks, particularly 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
    escription
    -0.78
    emaker
    -0.75
    ©¶æ
    -0.72
     encount
    -0.71
     tremend
    -0.71
    itability
    -0.71
    icz
    -0.70
     carbohyd
    -0.69
    ecycle
    -0.69
    everal
    -0.67
    POSITIVE LOGITS
     Anyway
    1.55
     ;)
    1.14
    Anyway
    1.04
     :)
    1.02
     Especially
    0.93
     :-)
    0.93
     Then
    0.90
     Let
    0.88
     Maybe
    0.86
     Repeat
    0.86
    Activations Density 0.363%

    No Known Activations