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. 501
    Prev
    Next
    INDEX
    Explanations

    sentences that end with punctuation

    oai_token-act-pair · gpt-3.5-turbo

    sentences that convey a sense of resolution or conclusions

    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
    isphere
    -0.89
    anni
    -0.76
     scheduled
    -0.75
    rique
    -0.75
    umerous
    -0.74
     finalized
    -0.74
     proposed
    -0.71
    ricanes
    -0.69
    auld
    -0.68
    ascus
    -0.68
    POSITIVE LOGITS
     Sometimes
    1.22
     Especially
    1.20
     Whether
    1.17
     Otherwise
    1.09
     Without
    1.05
     And
    1.05
     Whoever
    1.03
     If
    1.03
     When
    1.03
     That
    1.03
    Activations Density 0.469%

    No Known Activations