© 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. 7212
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating movement or direction, particularly related to going a long distance or making significant progress

    oai_token-act-pair · gpt-3.5-turbo

    directional terms or phrases indicating movement or progression, particularly "further" and "south."

    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
    ivery
    -0.59
     occurrence
    -0.58
     operation
    -0.58
     closure
    -0.57
    TE
    -0.55
     Scal
    -0.55
     collaboration
    -0.54
    operation
    -0.53
     Liver
    -0.53
    iqueness
    -0.53
    POSITIVE LOGITS
    izont
    0.83
    iless
    0.80
     stairs
    0.80
    wards
    0.79
    stairs
    0.77
    WARD
    0.75
     towards
    0.74
     unnoticed
    0.74
    raviolet
    0.70
     sidx
    0.70
    Activations Density 0.160%

    No Known Activations