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

    Neuronpedia

    APICircuit 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. 11-RES-JB
    6. 19698
    Prev
    Next
    INDEX
    Explanations

    locations or places described with specific characteristics or attributes, such as rundown, small, or wealthy

    oai_token-act-pair · gpt-3.5-turbo

    descriptors of living conditions and housing types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    earable
    -0.86
    Tags
    -0.84
    rations
    -0.84
    inators
    -0.83
    oppers
    -0.83
    UGC
    -0.82
    */(
    -0.81
    clips
    -0.81
    NetMessage
    -0.78
    ussions
    -0.78
    POSITIVE LOGITS
     village
    1.55
     town
    1.45
     cottage
    1.42
     mansion
    1.37
     farm
    1.31
     monastery
    1.29
     suburb
    1.29
     vill
    1.28
     castle
    1.27
     enclave
    1.26
    Activations Density 0.304%

    No Known Activations