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. 15576
    Prev
    Next
    INDEX
    Explanations

    ISBN numbers

    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
    1343
    +0.16
    0.5%
    573
    +0.10
    0.3%
    453
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1784
    +0.16
    0.02
    1786
    +0.10
    0.01
    471
    +0.09
    0.01
    Negative Logits
     depic
    -2.07
     disagre
    -2.06
     indestru
    -2.06
     increa
    -2.02
     shenan
    -2.00
     encomp
    -1.99
     impra
    -1.97
     intersper
    -1.97
     apprehen
    -1.97
     reluct
    -1.96
    POSITIVE LOGITS
    ISBN
    0.92
     ISBN
    0.91
     محفوظة
    0.74
    isbn
    0.74
    utf
    0.65
    ─
    0.64
    Sinopsis
    0.61
    VIAF
    0.60
    Πηγές
    0.58
    <bos>
    0.58
    Activations Density 0.036%

    No Known Activations