© 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. 6-RES-JB
    11. 20624
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations, specifically bodies of water

    oai_token-act-pair · gpt-3.5-turbo

    phrases referring to geographical locations, particularly bodies of water

    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
    ername
    -0.87
    ually
    -0.74
    ily
    -0.71
    ernel
    -0.69
    ATURE
    -0.68
    rators
    -0.68
     arrang
    -0.68
    position
    -0.66
    employ
    -0.66
    :{
    -0.66
    POSITIVE LOGITS
     Galile
    0.93
     Plenty
    0.81
     Lakes
    0.79
     hops
    0.76
     Dover
    0.74
     paradise
    0.72
     Eden
    0.72
     Northeast
    0.72
     tears
    0.71
     mountains
    0.71
    Activations Density 0.129%

    No Known Activations