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. 685
    Prev
    Next
    INDEX
    Explanations

    discussion points in a community or political context

    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
    1150
    +0.13
    0.4%
    1445
    +0.08
    0.2%
    2034
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1445
    +0.13
    0.07
    1150
    +0.08
    0.03
    382
    +0.08
    0.06
    Negative Logits
     swarovski
    -1.18
     ecru
    -1.17
     tupperware
    -1.16
     hairc
    -1.14
     cushi
    -1.13
     nutella
    -1.09
     tricot
    -1.06
     oreo
    -1.00
     murano
    -0.98
     bordeaux
    -0.96
    POSITIVE LOGITS
     invokingState
    0.79
     ***!
    0.71
    Manbalar
    0.70
     discussing
    0.69
     PicClick
    0.67
     kasarigan
    0.66
    parsedMessage
    0.65
    Décès
    0.64
    ValueStyle
    0.62
    FieldBuilder
    0.62
    Activations Density 0.596%

    No Known Activations