© 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. 11-RES-JB
    11. 19321
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to urgency or critical processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ktop
    -0.70
    geries
    -0.62
    terness
    -0.60
    phal
    -0.54
    oided
    -0.54
    nsic
    -0.53
    zbollah
    -0.52
    alysed
    -0.50
     apologised
    -0.50
    intage
    -0.50
    POSITIVE LOGITS
    âĢ
    1.09
     âĢ
    1.08
    ãĢ
    1.03
     ðŁij
    0.97
    ÃĤ
    0.96
     ðŁ
    0.93
    ðŁ
    0.92
    ðŁij
    0.91
    ï¸ı
    0.90
    âľ
    0.90
    Activations Density 1.886%

    No Known Activations