© 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. 10-RES-JB
    11. 13835
    Prev
    Next
    INDEX
    Explanations

    directional cues or instructions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to orientation and positioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.74
    ontent
    -0.74
     Paste
    -0.72
    ufact
    -0.71
    ineries
    -0.68
    Mich
    -0.66
    esters
    -0.66
     Taste
    -0.65
     Soup
    -0.65
     Ore
    -0.65
    POSITIVE LOGITS
     downwards
    1.60
     sideways
    1.55
     perpendicular
    1.52
     downward
    1.45
     backwards
    1.42
     upward
    1.36
     backward
    1.34
     upwards
    1.31
     perpend
    1.30
     forwards
    1.27
    Activations Density 0.375%

    No Known Activations