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 · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 15624
    Prev
    Next
    INDEX
    Explanations

    mentions of specific street names or locations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    554
    +0.15
    0.5%
    597
    +0.14
    0.5%
    1464
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1464
    +0.15
    0.04
    554
    +0.14
    0.04
    437
    +0.14
    0.03
    Negative Logits
     krab
    -0.49
     bemer
    -0.49
     AssemblyCompany
    -0.47
    żdy
    -0.46
     unie
    -0.46
     vogel
    -0.45
    )_/¯
    -0.44
    曖昧さ回避
    -0.44
    edback
    -0.42
     schul
    -0.42
    POSITIVE LOGITS
     street
    1.28
    street
    1.16
    Street
    1.16
     Street
    1.12
     streets
    1.09
     STREET
    1.07
    streets
    1.00
    STREET
    1.00
     Streets
    0.95
    Streets
    0.94
    Activations Density 0.064%

    No Known Activations