© 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. 4-RES-JB
    11. 114
    Prev
    Next
    INDEX
    Explanations

    verbs related to acquiring knowledge and understanding

    oai_token-act-pair · gpt-3.5-turbo

    instances of realization or discovery

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

    No Comments

    Negative Logits
     preserving
    -0.67
     millenn
    -0.64
     preserves
    -0.61
    cius
    -0.59
     Historically
    -0.59
     preserved
    -0.58
     Beir
    -0.58
     theorem
    -0.58
     integrity
    -0.57
     alt
    -0.57
    POSITIVE LOGITS
    ounters
    0.80
    ãĤ¼ãĤ¦ãĤ¹
    0.80
    enges
    0.75
    ependence
    0.74
    TAIN
    0.74
    agues
    0.74
    oldown
    0.72
    obil
    0.72
    ONEY
    0.72
    livion
    0.71
    Activations Density 0.291%

    No Known Activations