© 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. 23530
    Prev
    Next
    INDEX
    Explanations

    behavioral patterns or actions of individuals, particularly focusing on how they behave in various situations

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "behave" and its different forms in relation to behavior

    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
    occup
    -0.75
     Solo
    -0.73
    ondo
    -0.72
    export
    -0.70
    fram
    -0.69
    user
    -0.67
    ixed
    -0.66
    oan
    -0.65
    val
    -0.64
    source
    -0.63
    POSITIVE LOGITS
     behaved
    1.27
     behave
    1.25
     behaves
    1.21
     behaving
    1.06
     behavi
    0.99
     behaviours
    0.96
     behaviour
    0.91
     Behavior
    0.89
     behavior
    0.88
     behaviors
    0.88
    Activations Density 0.006%

    No Known Activations