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. 13612
    Prev
    Next
    INDEX
    Explanations

    information related to historical events and specific details of objects or concepts

    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
    1150
    +0.17
    0.5%
    1510
    +0.14
    0.4%
    630
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    630
    +0.17
    0.02
    580
    +0.14
    0.02
    163
    +0.13
    0.02
    Negative Logits
    astéro
    -0.82
     frankfurt
    -0.81
    Eksteraj
    -0.79
    ">...
    -0.78
     Redacción
    -0.75
    Răsp
    -0.74
    Glej
    -0.73
    Autoritní
    -0.73
    Переваги
    -0.73
    Și
    -0.72
    POSITIVE LOGITS
    ).
    0.64
    )
    0.63
    }
    0.61
    ].
    0.61
    );
    0.60
    2
    0.59
    ↵↵
    0.58
    <eos>
    0.58
     مشين
    0.58
    .
    0.58
    Activations Density 0.039%

    No Known Activations