© 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. 12896
    Prev
    Next
    INDEX
    Explanations

    words related to causality or attribution of actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that discuss occurrences or events related to the word "come."

    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
    vell
    -0.63
    oris
    -0.62
    orthodox
    -0.61
    gem
    -0.60
    ingham
    -0.60
    ewitness
    -0.60
    archives
    -0.60
    ablo
    -0.60
    eering
    -0.59
    Jacob
    -0.59
    POSITIVE LOGITS
     undone
    1.00
     naturally
    0.89
     nowhere
    0.80
     crashing
    0.79
     down
    0.79
     pouring
    0.75
     along
    0.74
     closest
    0.72
     apart
    0.72
     flooding
    0.71
    Activations Density 0.059%

    No Known Activations