© 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. 6-RES-JB
    11. 7870
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking decisive actions or making significant decisions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that imply extraction or removal

    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
    orously
    -0.83
    orld
    -0.78
    ould
    -0.73
    esa
    -0.71
    staking
    -0.70
    shaw
    -0.68
    pton
    -0.67
    umbered
    -0.67
    etimes
    -0.65
    ingham
    -0.64
    POSITIVE LOGITS
    stretched
    0.98
     levers
    0.74
    wards
    0.72
    rage
    0.69
    doors
    0.67
    ta
    0.65
    casts
    0.63
     microphones
    0.63
     stitches
    0.62
    WARD
    0.62
    Activations Density 0.028%

    No Known Activations