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. 15775
    Prev
    Next
    INDEX
    Explanations

    discussion related to social media and digital threats

    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
    599
    +0.14
    0.4%
    468
    +0.13
    0.4%
    1042
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    599
    +0.14
    0.09
    468
    +0.13
    0.05
    1173
    +0.10
    0.04
    Negative Logits
     unwarran
    -1.53
     unspeak
    -1.50
     indestru
    -1.47
     disagre
    -1.46
     impractica
    -1.41
     tolerably
    -1.41
     unlaw
    -1.40
     reluct
    -1.40
     hairc
    -1.37
     vainly
    -1.29
    POSITIVE LOGITS
     ortop
    0.88
     makro
    0.81
    <bos>
    0.75
     rú
    0.75
     pú
    0.75
     klinik
    0.74
     fono
    0.74
     alkoh
    0.73
     dó
    0.73
     republi
    0.71
    Activations Density 0.749%

    No Known Activations