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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 3429
    Prev
    Next
    INDEX
    Explanations

    locations and directional words

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases related to geographical locations or movements in space

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    ocument
    -0.74
    Background
    -0.73
     Flavoring
    -0.71
    fact
    -0.70
    suits
    -0.68
    isu
    -0.67
     Pengu
    -0.67
    workers
    -0.64
    ocus
    -0.64
    itizen
    -0.64
    POSITIVE LOGITS
     stairs
    1.32
     aisle
    1.32
     rabbit
    1.14
     slope
    1.13
     hallway
    1.13
     throats
    1.13
     escal
    1.10
     hill
    1.09
     corridor
    1.07
     alley
    1.07
    Activations Density 0.077%

    No Known Activations