© 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. 10-RES-JB
    11. 20254
    Prev
    Next
    INDEX
    Explanations

    phrases related to living in different situations or conditions

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to living conditions and environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¿½
    -0.77
    catentry
    -0.77
     attm
    -0.73
    offer
    -0.70
    killed
    -0.69
    try
    -0.67
    opoulos
    -0.65
     Wrest
    -0.64
    needed
    -0.64
     ingred
    -0.64
    POSITIVE LOGITS
     exile
    1.05
     caves
    1.05
     harmony
    1.00
     captivity
    0.97
     accordance
    0.96
     perpetual
    0.93
     tents
    0.92
     poverty
    0.92
     limbo
    0.85
     fear
    0.84
    Activations Density 0.120%

    No Known Activations