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. 13481
    Prev
    Next
    INDEX
    Explanations

    mentions of sports teams and player accolades, particularly related to basketball and football

    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
    1081
    +0.11
    0.3%
    897
    +0.09
    0.3%
    486
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1081
    +0.11
    0.05
    405
    +0.09
    0.03
    1467
    +0.09
    0.03
    Negative Logits
    troppo
    -0.49
     edel
    -0.49
    getCmp
    -0.48
    toolStrip
    -0.46
    closePath
    -0.46
     verru
    -0.45
    DataPropertyName
    -0.44
    sendStatus
    -0.43
    Quanto
    -0.43
    FORME
    -0.42
    POSITIVE LOGITS
     découver
    0.59
    quares
    0.59
    ücksich
    0.58
     shippuden
    0.56
     fernando
    0.54
    AILABILITY
    0.54
     rafael
    0.53
     découv
    0.52
    °;
    0.52
     kyo
    0.51
    Activations Density 0.170%

    No Known Activations