© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 18543
    Prev
    Next
    INDEX
    Explanations

    words related to rumors and upcoming events

    oai_token-act-pair · gpt-3.5-turbo

    content related to rumors and speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ateurs
    -0.83
    @#&
    -0.79
    ¬¼
    -0.78
    ictionary
    -0.75
     careless
    -0.73
    ername
    -0.72
    ruciating
    -0.72
    ashington
    -0.70
    gencies
    -0.70
     Economist
    -0.69
    POSITIVE LOGITS
     upcoming
    1.28
     TBA
    1.27
     rumored
    1.21
     forthcoming
    1.18
     sequels
    1.10
     TBD
    1.01
     imminent
    1.01
     future
    1.01
     teaser
    0.99
     sequel
    0.97
    Activations Density 0.585%

    No Known Activations