© 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. 6-RES-JB
    11. 13577
    Prev
    Next
    INDEX
    Explanations

    phrases related to approaching or standing near a target

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe physical movement towards a location or object

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hare
    -0.70
    rences
    -0.69
     Perspective
    -0.65
    Works
    -0.64
    oche
    -0.63
    United
    -0.61
     Controlled
    -0.60
    green
    -0.60
    hops
    -0.59
    Green
    -0.59
    POSITIVE LOGITS
     defend
    0.81
     compensate
    0.80
     date
    0.75
    pload
    0.74
     Leilan
    0.70
     baseline
    0.70
     ensure
    0.69
    dos
    0.69
     pasture
    0.68
     insure
    0.65
    Activations Density 0.049%

    No Known Activations