© 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. 10-RES-JB
    11. 21540
    Prev
    Next
    INDEX
    Explanations

    phrases related to news headlines

    oai_token-act-pair · gpt-3.5-turbo

    events involving legal actions or charges

    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
    Newsletter
    -0.92
    _.
    -0.77
     thereof
    -0.74
    ··
    -0.72
    _-
    -0.72
     blah
    -0.69
     etc
    -0.68
     thereafter
    -0.67
    ãĢĤ
    -0.66
     aforementioned
    -0.66
    POSITIVE LOGITS
     Belfast
    0.94
     apologise
    0.85
     apologised
    0.83
     honoured
    0.78
    zens
    0.69
     organisers
    0.68
     £
    0.68
    Published
    0.68
     watchdog
    0.68
    Warning
    0.68
    Activations Density 0.453%

    No Known Activations