© 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. 16876
    Prev
    Next
    INDEX
    Explanations

    news organizations and journalists

    oai_token-act-pair · gpt-3.5-turbo

    mentions of news organizations and related entities

    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
     cumbers
    -0.75
     boiler
    -0.67
     replication
    -0.64
     inclusion
    -0.63
     erosion
    -0.63
     captcha
    -0.62
     baggage
    -0.62
     snowball
    -0.61
     warranties
    -0.61
     turbulence
    -0.60
    POSITIVE LOGITS
    biz
    0.98
    /)
    0.96
    )!
    0.96
    )
    0.96
    Jr
    0.91
    MN
    0.87
    _.
    0.84
    _
    0.83
    pai
    0.82
    /,
    0.81
    Activations Density 0.100%

    No Known Activations