© 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. 13701
    Prev
    Next
    INDEX
    Explanations

    phrases indicating spatial orientation and direction, specifically focusing on left and right movements

    oai_token-act-pair · gpt-3.5-turbo

    relationships and comparisons between opposing directions or choices

    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
     Appl
    -0.81
     Flavoring
    -0.70
    URA
    -0.69
    ©¶æ¥µ
    -0.68
     Dram
    -0.66
    76561
    -0.65
    Ag
    -0.65
    exempt
    -0.64
    MET
    -0.64
     Annual
    -0.63
    POSITIVE LOGITS
     right
    1.56
    right
    1.55
     RIGHT
    1.53
     Right
    1.48
     left
    1.44
    left
    1.41
    Right
    1.39
    Left
    1.35
     Left
    1.32
     centre
    1.32
    Activations Density 0.123%

    No Known Activations