© 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. 8-RES-JB
    11. 16755
    Prev
    Next
    INDEX
    Explanations

    phrases related to warning signs or indications of future events

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to future consequences or predictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.64
     Zup
    -0.62
     pumps
    -0.58
     pawn
    -0.56
    opol
    -0.56
    Downloadha
    -0.56
     mins
    -0.55
    utterstock
    -0.55
     quotes
    -0.55
     cite
    -0.55
    POSITIVE LOGITS
     eventual
    0.86
     future
    0.77
     hereafter
    0.72
    igsaw
    0.69
     humankind
    0.69
    ensable
    0.69
     apocalypse
    0.68
     nascent
    0.67
     mankind
    0.67
     impending
    0.65
    Activations Density 0.882%

    No Known Activations