© 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. 800
    Prev
    Next
    INDEX
    Explanations

    mentions of a particular person or their characteristics

    oai_token-act-pair · gpt-3.5-turbo

    mentions of omitted information or criticisms

    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
     roundup
    -0.75
    yssey
    -0.74
     )]
    -0.67
     Lancaster
    -0.66
    OSH
    -0.62
     Garage
    -0.61
    ardless
    -0.61
     largeDownload
    -0.61
    mire
    -0.60
    starter
    -0.59
    POSITIVE LOGITS
     altogether
    1.25
     caveats
    1.20
     caveat
    1.00
     inconvenient
    0.96
     fact
    0.94
     possibility
    0.93
     facts
    0.91
     disadvantages
    0.89
     differences
    0.89
     entirely
    0.88
    Activations Density 0.524%

    No Known Activations