© 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. 8073
    Prev
    Next
    INDEX
    Explanations

    phrases related to memory and enduring legacy

    oai_token-act-pair · gpt-3.5-turbo

    themes related to remembrance and legacy

    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
    furt
    -0.83
    Minimum
    -0.77
    compliance
    -0.75
    axis
    -0.73
     coercion
    -0.73
    SpaceEngineers
    -0.72
    setup
    -0.71
    coord
    -0.71
     beta
    -0.70
     Setup
    -0.70
    POSITIVE LOGITS
     remem
    1.92
     remembrance
    1.89
     memories
    1.82
     memorial
    1.67
     remembered
    1.62
     Memories
    1.60
     reminis
    1.56
     Remem
    1.55
     commemor
    1.52
     recol
    1.51
    Activations Density 1.053%

    No Known Activations