© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 19150
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations or associations with places

    oai_token-act-pair · gpt-3.5-turbo

    frequency of specific prepositions and contextual phrases related to location or action

    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
     arrang
    -0.70
     behaved
    -0.61
     challeng
    -0.59
     Cyborg
    -0.58
     acquainted
    -0.58
    DragonMagazine
    -0.57
    RAY
    -0.57
    RAFT
    -0.56
    IBLE
    -0.56
     anyways
    -0.56
    POSITIVE LOGITS
    aband
    0.66
     Tre
    0.65
    irin
    0.61
     CPC
    0.58
    shock
    0.57
    endar
    0.57
    isse
    0.56
    ago
    0.56
    western
    0.56
    Wars
    0.54
    Activations Density 0.433%

    No Known Activations