© 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. 1-RES-JB
    11. 3173
    Prev
    Next
    INDEX
    Explanations

    the action of fleeing or escaping

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "flee" and related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ammy
    -0.76
    arist
    -0.75
    arya
    -0.70
    uyomi
    -0.69
    */(
    -0.68
    imen
    -0.67
    benef
    -0.64
    ocr
    -0.64
    Grant
    -0.64
    obyl
    -0.63
    POSITIVE LOGITS
     flee
    1.13
     fleeing
    1.01
    escape
    0.83
    eware
    0.77
     fled
    0.76
     vanish
    0.70
     Calais
    0.69
    VILLE
    0.69
    odge
    0.69
    ishable
    0.69
    Activations Density 0.004%

    No Known Activations