© 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. 7-RES-JB
    11. 11645
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the author's disclaimer or lack of representation of others' views

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating authorship and opinions that clarify that the views expressed are those of an individual rather than a collective or organizational stance

    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
    delay
    -0.70
     shuffle
    -0.67
    zza
    -0.67
     FDR
    -0.66
     bottleneck
    -0.66
    trap
    -0.63
     Faster
    -0.62
    aunts
    -0.61
    gun
    -0.61
     Mn
    -0.61
    POSITIVE LOGITS
     editorial
    0.89
     satire
    0.87
     trademarks
    0.86
    çīĪ
    0.84
     opinions
    0.84
     copyrighted
    0.83
    ashington
    0.70
     tentative
    0.69
     belong
    0.69
     affiliate
    0.68
    Activations Density 0.226%

    No Known Activations