© 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. 13657
    Prev
    Next
    INDEX
    Explanations

    specific locations or areas identified by the term "intersection"

    oai_token-act-pair · gpt-3.5-turbo

    references to different intersections, particularly in a geographical or conceptual context

    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
    apons
    -0.79
    sonian
    -0.76
    wagen
    -0.71
    warm
    -0.70
    unker
    -0.68
    ciples
    -0.67
    pload
    -0.63
    oult
    -0.63
    zn
    -0.63
    uten
    -0.63
    POSITIVE LOGITS
     intersection
    0.82
     intersections
    0.76
    lane
    0.74
    alities
    0.74
     Sakuya
    0.74
     mund
    0.70
    cross
    0.70
     Beir
    0.69
    course
    0.69
     Frie
    0.68
    Activations Density 0.025%

    No Known Activations