© 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 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. 6-RES-JB
    11. 4141
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific locations, particularly "Fort" followed by a location name

    oai_token-act-pair · gpt-3.5-turbo

    references to the location "Fort" along with associated place names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.70
     subscribing
    -0.64
    Companies
    -0.64
    Publisher
    -0.61
    soever
    -0.60
    Magikarp
    -0.59
    âĹ¼
    -0.59
    akers
    -0.58
     eclipse
    -0.58
    lyak
    -0.57
    POSITIVE LOGITS
    uitous
    1.39
    itude
    1.24
    ieth
    1.10
     Lauderdale
    1.04
    dinand
    1.02
    itud
    0.98
    resses
    0.96
    oise
    0.96
     Fort
    0.95
    folios
    0.90
    Activations Density 0.019%

    No Known Activations