© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 11073
    Prev
    Next
    INDEX
    Explanations

    sentences or statements that end with a punctuation mark

    oai_token-act-pair · gpt-3.5-turbo

    sentences that indicate or conclude information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     extinguished
    -0.82
     replen
    -0.74
     rebirth
    -0.74
     extinct
    -0.71
     docks
    -0.71
     weddings
    -0.70
     rigs
    -0.70
     destiny
    -0.70
     expend
    -0.70
     insur
    -0.69
    POSITIVE LOGITS
     Specifically
    1.41
     Among
    1.40
     Included
    1.40
     Below
    1.37
     Notably
    1.31
     Here
    1.27
     Topics
    1.25
     According
    1.21
     Readers
    1.20
     Essentially
    1.18
    Activations Density 0.390%

    No Known Activations