© 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. 6-RES-JB
    11. 18836
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a call to action

    oai_token-act-pair · gpt-3.5-turbo

    phrases that start with "Take" followed by a numerical value

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     advertised
    -0.73
     agre
    -0.69
     brill
    -0.65
    iege
    -0.64
     disg
    -0.63
    earances
    -0.63
    ulo
    -0.63
    Cong
    -0.63
     david
    -0.63
    ancial
    -0.62
    POSITIVE LOGITS
    aways
    1.48
    away
    1.07
    overs
    1.01
     advantage
    0.94
     aback
    0.93
     heed
    0.93
    offs
    0.82
    OVER
    0.80
    weed
    0.78
     care
    0.78
    Activations Density 0.078%

    No Known Activations