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. 15816
    Prev
    Next
    INDEX
    Explanations

    information related to web servers and programming, with a focus on headers, server functionality, compiler behavior, and app features

    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
    876
    +0.17
    0.5%
    1559
    +0.07
    0.2%
    690
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2044
    +0.17
    0.05
    876
    +0.07
    -0.01
    1415
    +0.07
    0.02
    Negative Logits
     Keny
    -1.28
     Khart
    -1.23
     Juf
    -1.22
     silikon
    -1.18
     Bartholo
    -1.18
     Punj
    -1.11
     Magdal
    -1.11
     kooper
    -1.10
     Gorb
    -1.08
     kriminal
    -1.07
    POSITIVE LOGITS
     automatically
    0.78
     itself
    0.68
     ModelRenderer
    0.65
    SneakyThrows
    0.63
    IonicModule
    0.63
    automatically
    0.62
    Pozdrawiam
    0.62
     hObject
    0.59
    matchCondition
    0.59
    TokenNameLPAREN
    0.59
    Activations Density 0.348%

    No Known Activations