© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 12749
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the passage of time or sequences of events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "After."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lever
    -0.71
     heritage
    -0.68
     design
    -0.66
     better
    -0.65
     distinguished
    -0.65
     tuned
    -0.64
     fault
    -0.63
     reflex
    -0.62
     simpl
    -0.62
     preferred
    -0.61
    POSITIVE LOGITS
    After
    2.91
    Following
    2.18
    During
    2.07
    Before
    2.02
     After
    1.95
    Once
    1.91
    Upon
    1.86
    Shortly
    1.85
     Afterwards
    1.84
    When
    1.78
    Activations Density 0.020%

    No Known Activations