© 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. 8-RES-JB
    11. 22563
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences or sensations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe personal experiences and sensations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enta
    -0.85
    hatt
    -0.84
    law
    -0.78
    corn
    -0.77
    raft
    -0.75
    ature
    -0.75
    loader
    -0.73
    loaded
    -0.72
    ffe
    -0.72
    iture
    -0.71
    POSITIVE LOGITS
     firsthand
    1.27
     hardships
    0.94
     difficulties
    0.93
     setbacks
    0.87
     homelessness
    0.86
     bouts
    0.82
     frustrations
    0.82
     debilitating
    0.81
     hardship
    0.81
     discomfort
    0.77
    Activations Density 0.049%

    No Known Activations