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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 12336
    Prev
    Next
    INDEX
    Explanations

    names of locations, specifically Beverly Hills

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Beverly" and related geographical references

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

    No Comments

    Negative Logits
    */(
    -1.09
    ebook
    -0.95
    emic
    -0.87
    ems
    -0.84
    udic
    -0.82
    ilver
    -0.75
    idem
    -0.74
    urgy
    -0.73
    ocalypse
    -0.72
    REDACTED
    -0.72
    POSITIVE LOGITS
     Hills
    1.17
     Beverly
    0.93
     Boulevard
    0.92
     Crusher
    0.89
     Hilton
    0.87
     Ny
    0.79
     Blvd
    0.78
     Bridge
    0.78
     Peninsula
    0.76
     Dame
    0.76
    Activations Density 0.012%

    No Known Activations