© 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. 9964
    Prev
    Next
    INDEX
    Explanations

    phrases related to leaving or escaping

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a desire or need to escape or leave a situation

    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
     heartbeat
    -0.70
     Emin
    -0.62
     Brach
    -0.59
     Hera
    -0.58
    guyen
    -0.54
     gallery
    -0.52
     Huang
    -0.51
     slideshow
    -0.51
     hemisphere
    -0.50
     waning
    -0.49
    POSITIVE LOGITS
    ta
    1.15
     alive
    0.84
    doors
    0.83
    bid
    0.80
    fitted
    0.78
    done
    0.78
    smart
    0.77
    stretched
    0.76
    played
    0.74
    last
    0.72
    Activations Density 0.057%

    No Known Activations