Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 4628
    Prev
    Next
    INDEX
    Explanations

    locations or entities named "Albany"

    oai_token-act-pair · gpt-3.5-turbo

    references to the location "Albany."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hypert
    -0.77
    Ped
    -0.76
    Steel
    -0.74
    ware
    -0.74
    RIP
    -0.72
    Mach
    -0.68
    pert
    -0.68
     RIP
    -0.68
     PV
    -0.68
    virt
    -0.67
    POSITIVE LOGITS
     Albany
    3.30
     Samoa
    1.09
     Albion
    1.08
     Alam
    1.03
     Nass
    1.02
     Arg
    1.02
     Salem
    0.99
     Sovere
    0.94
     Olympia
    0.93
     Canberra
    0.92
    Activations Density 0.051%

    No Known Activations