© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 23775
    Prev
    Next
    INDEX
    Explanations

    phrases related to the specific entity denoted by the letter "A"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter "A"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.72
     optics
    -0.63
    falls
    -0.61
     upstairs
    -0.59
    reports
    -0.58
    ]}
    -0.57
     XCOM
    -0.56
     eSports
    -0.55
     Everton
    -0.55
     noses
    -0.55
    POSITIVE LOGITS
    ussie
    1.28
    cknowled
    1.22
    cknow
    1.21
    verages
    1.19
    perture
    1.07
    BILITIES
    1.07
    uctions
    1.05
    UG
    1.04
    ryan
    1.02
    HA
    1.02
    Activations Density 0.085%

    No Known Activations