© 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. 17832
    Prev
    Next
    INDEX
    Explanations

    instances where an action is being carried out followed by a conditional or hypothetical scenario

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases indicating hypothetical situations

    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
    phrine
    -0.75
    verts
    -0.75
    available
    -0.72
    aukee
    -0.71
    hiba
    -0.70
    eph
    -0.69
    hess
    -0.66
    FTWARE
    -0.65
    estern
    -0.63
    uish
    -0.63
    POSITIVE LOGITS
    yip
    0.80
     nothing
    0.70
     they
    0.69
    acan
    0.68
     orchestr
    0.66
    hemy
    0.65
     indul
    0.62
    ociated
    0.62
     amalg
    0.61
    agnar
    0.61
    Activations Density 0.023%

    No Known Activations