© 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. 11-RES-JB
    11. 7598
    Prev
    Next
    INDEX
    Explanations

    reported events or news

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the act of reporting or referring to information and updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cair
    -0.63
    ophers
    -0.63
    chest
    -0.62
     Chamberlain
    -0.59
    agall
    -0.58
    opher
    -0.57
    ãĥŁ
    -0.57
     helium
    -0.56
    ierre
    -0.55
    neys
    -0.54
    POSITIVE LOGITS
    age
    0.87
    ufact
    0.79
    orial
    0.71
    udge
    0.69
    lies
    0.68
    orig
    0.66
    la
    0.65
    ounces
    0.64
     filed
    0.64
     surfaced
    0.64
    Activations Density 0.065%

    No Known Activations