© 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. 3-RES-JB
    11. 656
    Prev
    Next
    INDEX
    Explanations

    mentions of geographic locations or landscapes, specifically valleys

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical features, particularly valleys and craters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NAS
    -0.81
    Union
    -0.80
    rity
    -0.78
    NAT
    -0.73
     Digest
    -0.69
     Monetary
    -0.68
    Party
    -0.68
    oppable
    -0.66
    portation
    -0.65
     Inqu
    -0.64
    POSITIVE LOGITS
     valley
    1.28
     valleys
    1.10
     canyon
    0.86
     slope
    0.81
     corridor
    0.79
     floor
    0.78
     slopes
    0.77
     bushes
    0.75
     seams
    0.74
     caves
    0.74
    Activations Density 0.011%

    No Known Activations