© 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. 9895
    Prev
    Next
    INDEX
    Explanations

    phrases related to bringing characters or concepts to life

    oai_token-act-pair · gpt-3.5-turbo

    actions or events related to coming to life or becoming active

    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
    itiz
    -0.66
    ortunate
    -0.66
    ells
    -0.59
    nih
    -0.57
    href
    -0.57
     pse
    -0.56
     Tsukuyomi
    -0.56
    graph
    -0.56
     peas
    -0.55
    reciation
    -0.55
    POSITIVE LOGITS
     peacefully
    0.82
     anew
    0.80
     spontaneously
    0.80
     again
    0.73
     overnight
    0.73
     unexpectedly
    0.73
     amidst
    0.73
     with
    0.72
     withd
    0.71
     havoc
    0.68
    Activations Density 0.203%

    No Known Activations