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. 1547
    Prev
    Next
    INDEX
    Explanations

    references to sports teams, specifically the Anaheim Ducks

    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
    1328
    +0.20
    0.9%
    101
    +0.18
    0.8%
    156
    +0.17
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1328
    +0.20
    0.04
    156
    +0.18
    0.04
    101
    +0.17
    0.03
    Negative Logits
    XmlEnum
    -0.57
     disambiguazione
    -0.56
    FontOfSize
    -0.54
    providedIn
    -0.53
    RTLR
    -0.53
    FormBorderStyle
    -0.53
    ParallelGroup
    -0.51
    ProcessEvent
    -0.50
    jsii
    -0.49
    XmlAccessType
    -0.49
    POSITIVE LOGITS
    Duck
    0.84
     apprehen
    0.84
     foon
    0.81
     shewn
    0.81
     ftill
    0.81
     Duck
    0.80
     withal
    0.78
    duck
    0.78
     pamph
    0.77
     ftu
    0.77
    Activations Density 0.235%

    No Known Activations