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

    Neuronpedia

    Jacobian LensNEW
    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. 1729
    Prev
    Next
    INDEX
    Explanations

    phrases related to time or sequence

    oai_token-act-pair · gpt-3.5-turbo

    references to post-9/11 events and discussions

    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
     Rivals
    -0.73
     Wanted
    -0.70
     Cohn
    -0.70
     outnumbered
    -0.68
     Qiao
    -0.67
     DeV
    -0.64
     Sorce
    -0.62
     alone
    -0.62
     chants
    -0.60
    ;;;;;;;;;;;;
    -0.59
    POSITIVE LOGITS
    mortem
    1.41
    processing
    1.26
    traumatic
    1.15
    election
    1.14
    process
    1.12
    processor
    1.06
    condition
    1.06
    death
    1.04
    mort
    1.04
    industrial
    1.03
    Activations Density 0.025%

    No Known Activations