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. 354
    Prev
    Next
    INDEX
    Explanations

    information about finding vulnerabilities, conducting investigations, discovering flaws, and improvement methods

    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
    1413
    +0.13
    0.4%
    597
    +0.13
    0.4%
    559
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1413
    +0.13
    0.04
    559
    +0.13
    0.04
    597
    +0.11
    0.04
    Negative Logits
     désigne
    -0.72
     reconnaît
    -0.70
     résulte
    -0.66
     considère
    -0.64
     apparaît
    -0.61
     psycopg
    -0.61
     nomme
    -0.61
     prouve
    -0.60
     soutient
    -0.59
     rval
    -0.58
    POSITIVE LOGITS
     FIND
    1.13
    find
    1.10
     find
    1.07
    FIND
    1.04
     Find
    0.97
     finds
    0.96
    Find
    0.94
    finds
    0.90
     finding
    0.89
    finding
    0.86
    Activations Density 0.080%

    No Known Activations