© 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. 4-RES-JB
    11. 15250
    Prev
    Next
    INDEX
    Explanations

    phrases indicating surprise or disbelief

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the concept of being alone

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 4 - surprise

    No Comments

    Negative Logits
    ELD
    -0.80
    umper
    -0.80
    ula
    -0.74
    ulas
    -0.72
    roo
    -0.69
    ump
    -0.68
    istant
    -0.67
    iery
    -0.67
    ums
    -0.67
    ural
    -0.66
    POSITIVE LOGITS
    lihood
    0.80
    EngineDebug
    0.70
     suffice
    0.70
     necessarily
    0.65
    Reloaded
    0.63
    izont
    0.63
     dissu
    0.63
    acular
    0.62
     exceed
    0.62
     excluding
    0.62
    Activations Density 0.010%

    No Known Activations