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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6-RES-JB
    6. 5748
    Prev
    Next
    INDEX
    Explanations

    locations, especially cities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific geographical locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    colo
    -0.82
    potion
    -0.79
    icles
    -0.79
    algia
    -0.77
    omen
    -0.75
    airy
    -0.74
    bnb
    -0.73
    yah
    -0.73
    gging
    -0.72
    anyahu
    -0.72
    POSITIVE LOGITS
    wark
    0.87
    eston
    0.82
    atoon
    0.76
     Carolina
    0.72
    ãħĭãħĭ
    0.71
    ukong
    0.69
     Esk
    0.66
     Polk
    0.65
     Charleston
    0.64
     Volks
    0.64
    Activations Density 0.048%

    No Known Activations