© 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. 2-RES-JB
    11. 769
    Prev
    Next
    INDEX
    Explanations

    words associated with inactivity or lack of movement

    oai_token-act-pair · gpt-4-turbo

    phrases related to idleness or lack of activity

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to idleness or inactivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icz
    -0.84
     Flavoring
    -0.83
    alez
    -0.80
    obar
    -0.80
    ramid
    -0.77
    erion
    -0.74
    imet
    -0.71
    otide
    -0.70
    xual
    -0.70
    ulkan
    -0.69
    POSITIVE LOGITS
     idle
    1.23
     Idle
    0.90
     chatter
    0.90
     timers
    0.74
     timer
    0.69
     standby
    0.67
    bank
    0.65
     calories
    0.63
    ynes
    0.63
     pause
    0.63
    Activations Density 0.008%

    No Known Activations