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. 8377
    Prev
    Next
    INDEX
    Explanations

    terms related to information technology (IT) concepts and technological processes

    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
    +0.13
    0.4%
    1533
    +0.09
    0.3%
    1819
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1533
    +0.13
    0.03
    16
    +0.09
    0.06
    826
    +0.08
    0.03
    Negative Logits
     Abbé
    -1.13
     tremb
    -1.00
     embra
    -1.00
     deleter
    -0.99
     fta
    -0.98
     uniqu
    -0.96
     unve
    -0.93
     fto
    -0.91
     unden
    -0.91
     Shakspeare
    -0.91
    POSITIVE LOGITS
     each
    0.66
     whereby
    0.63
     someone
    0.61
    Geplaatst
    0.60
     whenever
    0.59
     individuals
    0.57
     instead
    0.56
     individual
    0.55
     somebody
    0.55
     you
    0.55
    Activations Density 0.559%

    No Known Activations