© 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. 11-RES-JB
    11. 10067
    Prev
    Next
    INDEX
    Explanations

    terms related to physical actions and movements, particularly those involving walking, running, jumping, and physical interactions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to group activities and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Understanding
    -0.81
    felt
    -0.77
     Continued
    -0.76
     Improvement
    -0.75
     Regarding
    -0.74
    states
    -0.74
    classified
    -0.73
    answered
    -0.73
     Horizon
    -0.73
    significant
    -0.72
    POSITIVE LOGITS
     snatch
    1.30
     lure
    1.27
     plunder
    1.26
     roam
    1.26
     gob
    1.23
     taunt
    1.23
     indulge
    1.23
     ambush
    1.23
     bribe
    1.22
     swoop
    1.21
    Activations Density 0.441%

    No Known Activations