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. 622
    Prev
    Next
    INDEX
    Explanations

    mentions related to donations or financial support

    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
    50
    +0.24
    0.9%
    1741
    +0.23
    0.8%
    1403
    +0.20
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.24
    0.10
    678
    +0.23
    0.09
    50
    +0.20
    0.07
    Negative Logits
     برابوك
    -0.68
    =""/>
    -0.63
    >(),
    -0.63
    !=-
    -0.62
    >();
    -0.61
    ByUrl
    -0.61
    );
    -0.60
    ])).
    -0.60
    ."/
    -0.58
     воздействия
    -0.58
    POSITIVE LOGITS
     affor
    1.18
     sappi
    1.11
     magis
    1.09
     peculi
    1.09
     cæ
    1.08
     cabrio
    1.06
     dsg
    1.06
     opport
    1.05
     robus
    1.05
     logitech
    1.04
    Activations Density 0.578%

    No Known Activations