© 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. 0-RES-JB
    11. 22285
    Prev
    Next
    INDEX
    Explanations

    words related to longevity or lasting qualities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to endurance and persistence over time

    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
     Junk
    -0.74
    Pod
    -0.70
     Setup
    -0.65
    bots
    -0.65
    opsis
    -0.65
     Shots
    -0.64
    shots
    -0.64
     Lets
    -0.63
    TT
    -0.62
    shot
    -0.62
    POSITIVE LOGITS
     enduring
    3.54
     abiding
    1.69
     endure
    1.58
     endured
    1.48
     lasting
    1.31
     persever
    1.28
     timeless
    1.26
     sustaining
    1.13
     everlasting
    1.10
     coping
    1.06
    Activations Density 0.028%

    No Known Activations