© 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. 9-RES-JB
    11. 15436
    Prev
    Next
    INDEX
    Explanations

    phrases related to information dissemination and communication, such as media mentions and social media interactions

    oai_token-act-pair · gpt-3.5-turbo

    references to services and communications in a modern context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "},"
    -0.88
    ankind
    -0.81
    ãĢį
    -0.80
    oeuv
    -0.80
    hei
    -0.80
    Ö
    -0.79
    ravings
    -0.79
    avour
    -0.78
    Äģ
    -0.76
    humane
    -0.76
    POSITIVE LOGITS
     FOIA
    0.93
     NYT
    0.93
     Politico
    0.91
     staffers
    0.91
     RNC
    0.91
     AOL
    0.89
     Gawker
    0.85
     Craigslist
    0.84
     redacted
    0.84
     IRC
    0.84
    Activations Density 1.626%

    No Known Activations