© 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. 9961
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals and their actions or positions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "was."

    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
     aspire
    -0.74
    ologies
    -0.73
    izable
    -0.70
     Needs
    -0.69
     decay
    -0.65
    ological
    -0.64
     Extend
    -0.63
    PsyNetMessage
    -0.63
     Gutenberg
    -0.63
     Franch
    -0.62
    POSITIVE LOGITS
     briefed
    1.26
     stunned
    1.12
     notified
    1.09
     alerted
    1.08
     saddened
    1.07
     shocked
    1.06
     dismay
    1.06
     surprised
    1.05
     appalled
    1.05
     astonished
    1.04
    Activations Density 0.193%

    No Known Activations