© 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. 7-RES-JB
    11. 1943
    Prev
    Next
    INDEX
    Explanations

    action words related to movement or progress

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "navigate" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endi
    -0.72
    onement
    -0.71
    rie
    -0.69
    die
    -0.69
    ¢
    -0.68
    riter
    -0.67
    rites
    -0.65
    asts
    -0.64
    venge
    -0.64
    inite
    -0.63
    POSITIVE LOGITS
     navigating
    1.02
     navigate
    1.01
     navig
    0.99
     Navigation
    0.91
     uphill
    0.82
     paths
    0.82
     navigation
    0.79
     menus
    0.76
    bilt
    0.75
    TAIN
    0.75
    Activations Density 0.030%

    No Known Activations