© 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. 0-RES-JB
    11. 3355
    Prev
    Next
    INDEX
    Explanations

    verbs related to escape or flight

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "flee" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NCT
    -0.78
    uth
    -0.72
    ould
    -0.71
    ipolar
    -0.69
     grading
    -0.67
     topical
    -0.65
     annotation
    -0.65
    ital
    -0.65
     Quality
    -0.63
    AMS
    -0.62
    POSITIVE LOGITS
     flee
    3.61
     fleeing
    3.14
     fled
    2.46
     escaping
    1.72
     fle
    1.51
     retreating
    1.50
     escape
    1.38
     exodus
    1.33
     escaped
    1.29
     evacuate
    1.23
    Activations Density 0.028%

    No Known Activations