© 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. 14866
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations such as streets or buildings

    oai_token-act-pair · gpt-3.5-turbo

    specific location names or terms related to addressing places

    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
    advertising
    -0.89
     fulfillment
    -0.72
    uations
    -0.64
    bats
    -0.63
    miss
    -0.62
    iosyncr
    -0.61
    ento
    -0.60
    utations
    -0.59
    gem
    -0.59
    sson
    -0.58
    POSITIVE LOGITS
    EStream
    0.83
    xual
    0.71
    xon
    0.69
    é¾
    0.66
     gradient
    0.64
    âĪĴ
    0.63
    ALT
    0.62
    spir
    0.60
    assic
    0.59
     Sheridan
    0.57
    Activations Density 0.293%

    No Known Activations