© 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. 11-RES-JB
    11. 7668
    Prev
    Next
    INDEX
    Explanations

    locations or positions described in relation to objects or devices on a surface or within a structure

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate location or positioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    conom
    -0.68
    soDeliveryDate
    -0.63
    urdue
    -0.61
    GV
    -0.59
    ãĤ£
    -0.58
    bug
    -0.57
    Nation
    -0.57
    terson
    -0.56
    phony
    -0.56
    uum
    -0.56
    POSITIVE LOGITS
     top
    1.21
    yx
    1.20
    top
    1.02
    ibaba
    1.01
     underside
    1.01
    slaught
    1.00
    sets
    0.96
     either
    0.94
    screen
    0.94
    erous
    0.93
    Activations Density 0.122%

    No Known Activations