© 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 EvalsExportsinterp-engineNEWAPI 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. 9723
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions and their consequences

    oai_token-act-pair · gpt-3.5-turbo

    the word "and" as well as associated conjunctions and elements of a complex narrative

    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
    OND
    -0.86
    DragonMagazine
    -0.75
    Morning
    -0.71
    DX
    -0.69
    CNN
    -0.69
    ¶
    -0.67
    RECT
    -0.67
    doi
    -0.66
    odcast
    -0.65
    ---------
    -0.65
    POSITIVE LOGITS
     thereby
    1.33
     thus
    1.25
     hence
    1.19
     consequently
    1.11
     therefore
    0.97
     thereafter
    0.94
     THEN
    0.94
     thence
    0.91
     subsequently
    0.90
     furthermore
    0.85
    Activations Density 0.578%

    No Known Activations