© 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. 10-RES-JB
    11. 20497
    Prev
    Next
    INDEX
    Explanations

    phrases related to spatial orientation and positions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to positional references or spatial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    forts
    -0.79
    abilities
    -0.75
    eers
    -0.75
    paio
    -0.73
    BIL
    -0.72
    erest
    -0.68
    arians
    -0.67
    ALLY
    -0.67
    orers
    -0.67
    ogens
    -0.64
    POSITIVE LOGITS
     spectrum
    1.31
     equation
    1.22
     globe
    1.12
     continuum
    1.10
     triangle
    1.06
     pyramid
    1.04
     ledger
    1.01
     compass
    1.00
     circle
    0.98
     rectangle
    0.98
    Activations Density 0.184%

    No Known Activations