© 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. 24511
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce or refer to a subsequent point or idea

    oai_token-act-pair · gpt-3.5-turbo

    references to studies or findings indicated by the word "this."

    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
    ickets
    -0.96
    warts
    -0.91
    cakes
    -0.90
    bugs
    -0.88
    stars
    -0.85
    okers
    -0.84
    rollers
    -0.84
    osponsors
    -0.82
    bats
    -0.81
    nuts
    -0.80
    POSITIVE LOGITS
     arrangement
    1.28
     latter
    1.21
     phenomenon
    1.21
     mechanism
    1.14
     discrepancy
    1.13
     aspect
    1.11
     methodology
    1.07
     technique
    1.07
     process
    1.07
     pecul
    1.06
    Activations Density 0.171%

    No Known Activations