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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 422
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical locations, particularly rural or country settings

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations and their attributes

    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
     Wallace
    -0.74
     Pell
    -0.67
     layoffs
    -0.66
     Ner
    -0.65
     Pett
    -0.63
     rearr
    -0.62
    ulla
    -0.61
     Rend
    -0.61
     mold
    -0.60
     neurons
    -0.60
    POSITIVE LOGITS
    country
    4.17
    Country
    2.03
    nation
    1.58
    packing
    1.53
    city
    1.38
     Country
    1.21
     country
    1.19
    street
    1.17
    woods
    1.12
    region
    1.11
    Activations Density 0.016%

    No Known Activations