Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8146
    Prev
    Next
    INDEX
    Explanations

    details about a character named Misty Knight, particularly focusing on her background, relationships, and experiences

    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
    509
    +0.09
    0.2%
    964
    +0.08
    0.2%
    1056
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    402
    +0.09
    0.06
    509
    +0.08
    0.06
    736
    +0.08
    0.06
    Negative Logits
     koni
    -0.52
     tenden
    -0.51
     hoj
    -0.50
     solida
    -0.50
    labus
    -0.50
     estekak
    -0.50
     vernac
    -0.48
     ladri
    -0.47
    asibility
    -0.47
     gesta
    -0.47
    POSITIVE LOGITS
    
    
    0.70
     bandeau
    0.69
     hairc
    0.65
     jouant
    0.64
     reft
    0.64
     Mlle
    0.63
     ecru
    0.63
     accident
    0.62
    secara
    0.61
     exé
    0.60
    Activations Density 0.547%

    No Known Activations