© 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. 17677
    Prev
    Next
    INDEX
    Explanations

    phrases related to descriptions of states or conditions

    oai_token-act-pair · gpt-3.5-turbo

    descriptors of chaotic and intense experiences

    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
    ospons
    -0.75
    burgh
    -0.74
     Clyde
    -0.74
     Patty
    -0.74
     Better
    -0.73
    Ted
    -0.72
     Scholars
    -0.72
     Supporters
    -0.69
     Ezek
    -0.69
     Younger
    -0.69
    POSITIVE LOGITS
     unpredict
    1.34
     unpredictable
    1.33
     uncontrolled
    1.27
     equilibrium
    1.25
     fluct
    1.25
     inertia
    1.25
     instantaneous
    1.24
     chaotic
    1.22
     erratic
    1.22
     uncontroll
    1.21
    Activations Density 0.461%

    No Known Activations