© 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. 11-RES-JB
    11. 15030
    Prev
    Next
    INDEX
    Explanations

    instances where the phrase "go back" or "go" is mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the action of going or returning somewhere

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icons
    -0.67
    bidden
    -0.64
    rely
    -0.63
     Watkins
    -0.61
    Category
    -0.60
    igo
    -0.59
     warrants
    -0.57
     Arri
    -0.57
     licenses
    -0.57
    inguished
    -0.56
    POSITIVE LOGITS
     ahead
    0.98
    ggle
    0.98
     buy
    0.95
     forth
    0.94
     fuck
    0.93
     pursue
    0.92
    verning
    0.91
     retrieve
    0.91
     investigate
    0.90
     explore
    0.88
    Activations Density 0.067%

    No Known Activations