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 · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 15255
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical locations, specifically related to the state of New Mexico

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1492
    +0.14
    0.7%
    950
    +0.12
    0.6%
    201
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.14
    0.06
    1013
    +0.12
    0.06
    324
    +0.11
    0.04
    Negative Logits
     intersper
    -1.24
     apprehen
    -1.12
     unspeak
    -0.99
     reluct
    -0.96
     pamph
    -0.96
     vainly
    -0.96
     overcrow
    -0.94
     underval
    -0.92
     tolerably
    -0.92
     aston
    -0.92
    POSITIVE LOGITS
    buquerque
    0.90
     Albuquerque
    0.87
     NM
    0.87
    NM
    0.83
     kano
    0.73
     gesta
    0.73
     rong
    0.73
     galo
    0.69
     zyn
    0.68
     ciga
    0.68
    Activations Density 0.623%

    No Known Activations