© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9390
    Prev
    Next
    INDEX
    Explanations

    words related to spatial directions such as 'left' and 'right'

    oai_token-act-pair · gpt-3.5-turbo

    directional references in visual or spatial contexts

    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
    ensable
    -0.78
    eson
    -0.78
    etimes
    -0.72
    anned
    -0.71
    doms
    -0.71
    avorite
    -0.71
    NRS
    -0.69
    ocide
    -0.68
    olitics
    -0.67
    allo
    -0.67
    POSITIVE LOGITS
     side
    1.01
     hand
    0.99
     flank
    0.90
     corner
    0.86
     sidebar
    0.86
     hemisphere
    0.85
    most
    0.85
     paw
    0.83
     Side
    0.83
    ħĭ
    0.82
    Activations Density 0.072%

    No Known Activations