© 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. 7517
    Prev
    Next
    INDEX
    Explanations

    acronyms or proper nouns related to various entities or organizations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to electronic gadgets and technology brands

    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
    ãĥīãĥ©ãĤ´ãĥ³
    -0.85
    itude
    -0.77
    itia
    -0.74
    cloth
    -0.73
    itud
    -0.71
    ãĥīãĥ©
    -0.70
    tenance
    -0.69
    ãĥĥãĤ¯
    -0.67
    mares
    -0.67
    icum
    -0.67
    POSITIVE LOGITS
    LER
    0.87
    SI
    0.83
    FAULT
    0.82
    REG
    0.82
    ASY
    0.82
    UAL
    0.81
    EO
    0.80
    BIT
    0.79
    LES
    0.79
    ILE
    0.78
    Activations Density 0.027%

    No Known Activations