© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 11483
    Prev
    Next
    INDEX
    Explanations

    mentions of significant life events or personal experiences

    oai_token-act-pair · gpt-3.5-turbo

    references to life and living experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iets
    -0.83
    yne
    -0.75
    swick
    -0.73
    ufficient
    -0.69
    ensor
    -0.68
    acks
    -0.68
    iegel
    -0.67
    leans
    -0.65
    utm
    -0.65
    acker
    -0.64
    POSITIVE LOGITS
     life
    3.66
    life
    2.80
     Life
    2.66
     LIFE
    2.50
    Life
    2.44
     lives
    2.06
     lifes
    1.75
     lifetime
    1.58
    lif
    1.58
     lifespan
    1.53
    Activations Density 0.035%

    No Known Activations