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. 435
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports events or achievements

    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
    764
    +0.17
    0.5%
    599
    +0.12
    0.3%
    2034
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    764
    +0.17
    0.07
    254
    +0.12
    0.06
    300
    +0.11
    0.06
    Negative Logits
     effe
    -2.31
     increa
    -2.15
     nece
    -2.14
     desir
    -2.12
     ftu
    -2.11
     aen
    -2.11
     fta
    -2.11
     guarante
    -2.06
     thut
    -2.03
     reluct
    -2.01
    POSITIVE LOGITS
     tomorrow
    0.88
    .
    0.86
     upcoming
    0.85
     soon
    0.83
    <bos>
    0.79
     next
    0.77
     expected
    0.76
    ;
    0.76
    。
    0.76
     forthcoming
    0.75
    Activations Density 0.686%

    No Known Activations