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. 708
    Prev
    Next
    INDEX
    Explanations

    numerical information related to sports teams and players

    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
    1343
    +0.10
    0.3%
    1788
    +0.08
    0.2%
    1082
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1788
    +0.10
    0.03
    2012
    +0.08
    0.03
    1847
    +0.07
    0.03
    Negative Logits
    VYMaps
    -0.61
    ManagedBean
    -0.52
    RESUMEN
    -0.50
    Parfait
    -0.50
    توض
    -0.48
    corollary
    -0.47
    ENODEV
    -0.47
    Freitag
    -0.46
    بسم
    -0.45
    nė
    -0.45
    POSITIVE LOGITS
     territo
    0.63
     sabbia
    0.61
     paes
    0.55
     cæ
    0.53
     cittad
    0.53
     spesa
    0.51
     pacient
    0.51
    redient
    0.51
    izielle
    0.50
     scolas
    0.49
    Activations Density 0.095%

    No Known Activations