© 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. 7584
    Prev
    Next
    INDEX
    Explanations

    events or actions that happened after a specific time or event

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "after" in relation to events or actions

    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
    aez
    -0.77
    geist
    -0.68
    onds
    -0.68
    女
    -0.68
    Sport
    -0.68
    eed
    -0.67
    Enabled
    -0.67
    =-=-=-=-=-=-=-=-
    -0.67
    IZE
    -0.66
    Mask
    -0.66
    POSITIVE LOGITS
    noon
    1.01
     completing
    0.96
     defeating
    0.89
     spending
    0.88
     undergoing
    0.88
     finishing
    0.86
     serving
    0.84
    wards
    0.81
     graduating
    0.81
     sustaining
    0.79
    Activations Density 0.099%

    No Known Activations