© 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. 23866
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a change or movement in a particular direction

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "on the rise."

    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
    ults
    -0.69
    MpServer
    -0.66
    اÙĦ
    -0.66
    itans
    -0.65
    zona
    -0.65
    onut
    -0.65
    md
    -0.64
    ricanes
    -0.64
    mini
    -0.64
    Together
    -0.64
    POSITIVE LOGITS
     hiatus
    1.20
     sale
    1.16
     pace
    1.05
     hold
    1.02
     track
    1.02
    erous
    1.00
     lockdown
    0.97
     cooldown
    0.96
     display
    0.95
     shaky
    0.90
    Activations Density 0.087%

    No Known Activations