© 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. 4-RES-JB
    11. 9156
    Prev
    Next
    INDEX
    Explanations

    news organizations and political figures

    oai_token-act-pair · gpt-3.5-turbo

    references to news organizations or major political figures

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

    No Comments

    Negative Logits
    }.
    -0.60
    $.
    -0.59
     thereof
    -0.55
    SPONSORED
    -0.55
     therein
    -0.52
    åĤ
    -0.51
    ··
    -0.51
    FactoryReloaded
    -0.50
     thereto
    -0.49
    ".[
    -0.48
    POSITIVE LOGITS
     meanwhile
    0.81
     spokesman
    0.72
     spokeswoman
    0.66
     reacted
    0.65
     spokesperson
    0.60
     declined
    0.56
    vik
    0.54
    ccording
    0.54
     responded
    0.54
     Releases
    0.53
    Activations Density 1.652%

    No Known Activations