© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12150
    Prev
    Next
    INDEX
    Explanations

    words related to movement and spatial relations

    oai_token-act-pair · gpt-3.5-turbo

    constructs involving spatial orientation or movement

    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
    idays
    -0.70
     Conservatives
    -0.67
     psychologists
    -0.61
    advertising
    -0.58
    DEM
    -0.58
     psychologist
    -0.58
     Tories
    -0.58
    IFIED
    -0.58
    llor
    -0.57
    Independent
    -0.56
    POSITIVE LOGITS
    between
    1.36
     front
    1.29
     situ
    1.06
    animate
    1.03
    vert
    1.02
     lieu
    0.97
     relation
    0.95
    versions
    0.95
    clusions
    0.94
    ching
    0.93
    Activations Density 0.209%

    No Known Activations