© 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. 8-RES-JB
    11. 9492
    Prev
    Next
    INDEX
    Explanations

    references or mentions of a specific person named "Her."

    oai_token-act-pair · gpt-3.5-turbo

    references to a significant individual named "Her."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rehe
    -0.65
    ypes
    -0.61
     blackout
    -0.60
    govtrack
    -0.60
    ozy
    -0.60
     veget
    -0.59
     tackle
    -0.59
     stru
    -0.58
     cele
    -0.58
    ãģį
    -0.57
    POSITIVE LOGITS
     Majesty
    1.55
    itage
    1.51
    metic
    1.26
    cule
    1.20
    ding
    1.16
    acl
    1.12
    mit
    1.11
    acles
    1.09
    itability
    1.09
    bal
    1.07
    Activations Density 0.043%

    No Known Activations