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. 10124
    Prev
    Next
    INDEX
    Explanations

    descriptions of spatial locations within a given area

    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
    1385
    +0.20
    0.6%
    906
    +0.17
    0.5%
    776
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    897
    +0.20
    0.04
    1385
    +0.17
    0.04
    825
    +0.12
    0.03
    Negative Logits
    intios
    -0.74
     Rasulullah
    -0.66
    XmlEnum
    -0.64
    ihnachten
    -0.63
    ControllerAdvice
    -0.61
    krish
    -0.58
    yanto
    -0.56
     Krieges
    -0.55
     poussière
    -0.54
     goutte
    -0.53
    POSITIVE LOGITS
     portion
    0.79
     side
    0.73
    Yeet
    0.64
     section
    0.61
    Tja
    0.59
    tldr
    0.59
    Derp
    0.59
     Facile
    0.57
     part
    0.57
    Xoxo
    0.55
    Activations Density 0.299%

    No Known Activations