© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-RES-JB
    11. 13598
    Prev
    Next
    INDEX
    Explanations

    words related to paths, directions, and movements that signal progress or change

    oai_token-act-pair · gpt-3.5-turbo

    references to trajectories and the concept of progress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zyme
    -0.67
    unts
    -0.66
    bery
    -0.65
    ression
    -0.63
    acted
    -0.60
    Mini
    -0.59
    akens
    -0.59
    ACTED
    -0.59
    sub
    -0.58
    inki
    -0.57
    POSITIVE LOGITS
     traject
    1.34
     trajectory
    1.29
    eers
    0.84
     paths
    0.75
     upwards
    0.72
     pige
    0.69
     Eag
    0.69
     routes
    0.69
    gradient
    0.69
    vich
    0.68
    Activations Density 0.011%

    No Known Activations