© 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. 7-RES-JB
    11. 18979
    Prev
    Next
    INDEX
    Explanations

    locations or positions denoted by the word "back"

    oai_token-act-pair · gpt-3.5-turbo

    references to spatial locations in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.80
    utical
    -0.71
    milo
    -0.69
    illin
    -0.69
    anned
    -0.62
    Fact
    -0.60
    Prof
    -0.60
    sbm
    -0.59
    apego
    -0.59
     Topic
    -0.58
    POSITIVE LOGITS
     vicinity
    0.87
     midst
    0.85
     compartment
    0.82
     closet
    0.81
     attic
    0.80
     courtyard
    0.77
     freezer
    0.77
     backfield
    0.74
     enclosure
    0.74
     woods
    0.73
    Activations Density 0.259%

    No Known Activations