© 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. 6-RES-JB
    11. 19815
    Prev
    Next
    INDEX
    Explanations

    words related to processes and actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to various processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arling
    -0.73
     Bust
    -0.70
    oft
    -0.70
    worthy
    -0.69
     ambitions
    -0.68
     Borders
    -0.67
    rift
    -0.66
    âĺ
    -0.65
    iesta
    -0.65
    ugs
    -0.64
    POSITIVE LOGITS
     extracting
    0.93
     process
    0.93
     selecting
    0.90
     obtaining
    0.89
     evaluating
    0.88
     determining
    0.87
    issance
    0.85
     sorting
    0.83
     proc
    0.83
     interviewing
    0.82
    Activations Density 0.163%

    No Known Activations