© 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. 9-RES-JB
    11. 4172
    Prev
    Next
    INDEX
    Explanations

    words related to directions or destinations

    oai_token-act-pair · gpt-3.5-turbo

    the word "to" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    few
    -0.66
    forcing
    -0.63
    mask
    -0.63
    IJ
    -0.60
    angered
    -0.58
     moder
    -0.56
     mishand
    -0.56
     Photographer
    -0.56
    note
    -0.55
     badly
    -0.55
    POSITIVE LOGITS
     shore
    0.85
     grips
    0.84
     completion
    0.84
     maximize
    0.83
     victory
    0.82
     destinations
    0.80
     conclusions
    0.78
     destination
    0.78
     orgasm
    0.77
     meet
    0.77
    Activations Density 0.167%

    No Known Activations