© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 16548
    Prev
    Next
    INDEX
    Explanations

    phrases related to screaming and yelling for help or distress

    oai_token-act-pair · gpt-3.5-turbo

    expressions of distress or pleas for help

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.83
     nostalg
    -0.75
     contrasts
    -0.72
     largely
    -0.71
     anecd
    -0.70
     pse
    -0.69
     ancest
    -0.69
     nostalgic
    -0.66
    clus
    -0.65
     pleasantly
    -0.65
    POSITIVE LOGITS
     STOP
    0.90
    Stop
    0.81
    shut
    0.78
     sir
    0.76
    stop
    0.75
     Stop
    0.74
    !"
    0.73
    Shut
    0.71
    hands
    0.71
    !'"
    0.71
    Activations Density 0.329%

    No Known Activations