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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 651
    Prev
    Next
    INDEX
    Explanations

    references to "Hill," particularly in the context of the Appalachian region or related cultural discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.22
    1.4%
    481
    +0.15
    1.0%
    489
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.22
    0.03
    489
    +0.15
    0.02
    699
    +0.13
    0.02
    Negative Logits
    <bos>
    -2.53
    IonicModule
    -0.74
    IEnumerator
    -0.66
    toMatchSnapshot
    -0.66
    <tfoot>
    -0.65
    MarshalTo
    -0.65
    </>
    
    -0.64
    ModelAttribute
    -0.64
    EditorGUILayout
    -0.64
    DataContract
    -0.64
    POSITIVE LOGITS
     maneu
    1.73
     reluct
    1.67
     increa
    1.64
     disagre
    1.63
     impra
    1.60
     inev
    1.58
     affor
    1.57
     resear
    1.56
     depic
    1.56
     Juf
    1.55
    Activations Density 0.035%

    No Known Activations