© 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. 16445
    Prev
    Next
    INDEX
    Explanations

    stressful situations or challenges

    oai_token-act-pair · gpt-3.5-turbo

    words related to psychological and physical burdens or difficulties

    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
    vez
    -0.87
    mingham
    -0.78
    Cola
    -0.74
    swick
    -0.70
    buquerque
    -0.70
    irrel
    -0.67
    escription
    -0.67
    enture
    -0.67
    iasco
    -0.66
    phis
    -0.66
    POSITIVE LOGITS
     inherent
    1.10
     inflicted
    1.10
     associated
    1.08
     incurred
    1.02
     caused
    1.01
     of
    1.01
     endured
    1.01
     imposed
    0.96
     faced
    0.96
     posed
    0.96
    Activations Density 0.239%

    No Known Activations