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. 3114
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and beliefs, especially related to advocating for a specific cause or disagreeing with others

    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
    1978
    +0.13
    0.4%
    1150
    +0.08
    0.2%
    823
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.13
    0.05
    1631
    +0.08
    0.04
    1166
    +0.08
    0.05
    Negative Logits
     NTIS
    -0.77
     actionTypes
    -0.65
     unlaw
    -0.62
     animés
    -0.61
     dovr
    -0.59
     bahay
    -0.58
     CiNii
    -0.57
     kuni
    -0.57
     naer
    -0.57
     ftu
    -0.57
    POSITIVE LOGITS
     CreateTagHelper
    0.51
    preso
    0.47
    ionais
    0.44
     chuy
    0.42
    ricanes
    0.42
     duong
    0.41
    <bos>
    0.40
    іан
    0.40
    níku
    0.39
    "/",
    0.39
    Activations Density 0.399%

    No Known Activations