© 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. 10-RES-JB
    11. 20407
    Prev
    Next
    INDEX
    Explanations

    phrases related to inciting or intensifying emotions, reactions, or behaviors

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating emotional expressions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    document
    -0.72
    facing
    -0.71
     describ
    -0.69
     indemn
    -0.68
    face
    -0.68
    utan
    -0.67
    escription
    -0.65
    iguous
    -0.64
     mattered
    -0.63
    fax
    -0.63
    POSITIVE LOGITS
     thirst
    1.45
     passions
    1.44
     imagination
    1.36
     appetite
    1.36
     flames
    1.22
     dormant
    1.22
     imag
    1.18
     enthusiasm
    1.18
     curiosity
    1.17
     craving
    1.16
    Activations Density 0.357%

    No Known Activations