© 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. 17385
    Prev
    Next
    INDEX
    Explanations

    mentions of various events or occurrences related to reporting, news, or meetings

    oai_token-act-pair · gpt-3.5-turbo

    references to media outlets and reports

    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
    afety
    -0.68
    conservancy
    -0.61
    uesday
    -0.54
    idth
    -0.54
    ASHINGTON
    -0.53
    ometimes
    -0.52
     CHRIST
    -0.51
     whisky
    -0.51
    Blood
    -0.50
     Roses
    -0.49
    POSITIVE LOGITS
    mentioned
    0.65
    sth
    0.64
     findings
    0.64
     observations
    0.62
     piece
    0.61
     mentioned
    0.61
    hesis
    0.60
     citation
    0.58
     coincided
    0.57
     debacle
    0.57
    Activations Density 0.733%

    No Known Activations