© 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. 12221
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant events or notable occurrences

    oai_token-act-pair · gpt-3.5-turbo

    highly significant cultural and political events or phenomena

    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
    çīĪ
    -0.80
    çī
    -0.71
    aleb
    -0.64
    ruciating
    -0.64
    天
    -0.63
    instead
    -0.63
    200000
    -0.61
    tiny
    -0.61
    ãĥĥ
    -0.61
    å¿
    -0.60
    POSITIVE LOGITS
     EVER
    1.81
     imaginable
    1.81
     ever
    1.78
    ever
    1.41
     Ever
    1.27
     conceivable
    1.16
    Ever
    1.13
     anywhere
    1.08
     possible
    1.03
     alive
    0.89
    Activations Density 0.263%

    No Known Activations