© 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. 7-RES-JB
    11. 22849
    Prev
    Next
    INDEX
    Explanations

    words related to directions and positions, specifically the term "Left" with different numerical values indicating varying degrees of relevance or importance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "left."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    glomer
    -0.77
    andise
    -0.77
    riott
    -0.70
    issance
    -0.70
    idated
    -0.68
    è¦ļéĨĴ
    -0.68
     conduc
    -0.67
    alez
    -0.65
    NRS
    -0.65
    antz
    -0.65
    POSITIVE LOGITS
    overs
    1.27
    wing
    1.10
    hander
    0.94
    wich
    0.89
    ward
    0.89
    fing
    0.86
     wing
    0.80
     handed
    0.80
    handed
    0.80
     hemisphere
    0.78
    Activations Density 0.041%

    No Known Activations