© 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. 9-RES-JB
    11. 18196
    Prev
    Next
    INDEX
    Explanations

    geographical locations such as towns, mountains, bays, and roads

    oai_token-act-pair · gpt-3.5-turbo

    geographic locations and natural landmarks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     asses
    -0.71
     pes
    -0.71
    ikhail
    -0.67
    OST
    -0.66
     gladly
    -0.64
     yen
    -0.63
     hormonal
    -0.63
     reproduce
    -0.62
    olded
    -0.62
    someone
    -0.61
    POSITIVE LOGITS
     Resort
    1.31
     Cemetery
    1.29
     Farms
    1.19
     Parkway
    1.17
     Apart
    1.17
     Lodge
    1.14
     Reserv
    1.13
     Rd
    1.13
     Observatory
    1.12
     Ranch
    1.11
    Activations Density 0.179%

    No Known Activations