© 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. 8-RES-JB
    11. 17871
    Prev
    Next
    INDEX
    Explanations

    people who are positioned on the left side of an image or scene

    oai_token-act-pair · gpt-3.5-turbo

    references to the side positions in a context, such as "left" and "right"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Traps
    -0.67
    gent
    -0.66
    Rule
    -0.64
    utenberg
    -0.61
    DERR
    -0.61
    APTER
    -0.61
    ensity
    -0.59
    alled
    -0.59
    ARDIS
    -0.58
    CONCLUS
    -0.58
    POSITIVE LOGITS
     caption
    0.82
     portraits
    0.80
     screenshot
    0.78
     photo
    0.75
     pictured
    0.70
     Courtesy
    0.70
     flanked
    0.70
     shoulder
    0.69
     IMAGES
    0.68
    left
    0.68
    Activations Density 0.046%

    No Known Activations