© 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. 11-RES-JB
    11. 18774
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a specific point or period in time

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "at a time when."

    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
    cause
    -0.89
    emort
    -0.80
    igmatic
    -0.78
    operator
    -0.75
    gon
    -0.74
    nesday
    -0.74
    edited
    -0.73
    gal
    -0.71
    MpServer
    -0.70
    iliate
    -0.69
    POSITIVE LOGITS
     tensions
    1.01
     temperatures
    0.86
     there
    0.83
     hostilities
    0.81
     many
    0.80
     relations
    0.79
     nobody
    0.77
     everyone
    0.73
     we
    0.72
     unemployment
    0.71
    Activations Density 0.155%

    No Known Activations