Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 12-RES-JB
    6. 157
    Prev
    Next
    INDEX
    Explanations

    references to the "Star Trek" franchise and its elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.12.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    12
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.21
    0.8%
    86
    +0.10
    0.4%
    1035
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    86
    +0.21
    0.03
    304
    +0.10
    -0.00
    227
    +0.09
    0.05
    Negative Logits
    <bos>
    -2.05
     intptr
    -0.75
    public
    -0.74
     censiti
    -0.73
     EconPapers
    -0.73
     utafitiHapana
    -0.69
     <<<<<<<<<<<<<<
    -0.68
    HideFlags
    -0.66
    IVEREF
    -0.65
     mergeFrom
    -0.65
    POSITIVE LOGITS
     increa
    1.88
     affor
    1.85
     emphat
    1.77
     excru
    1.73
     ecru
    1.65
     perfet
    1.65
     disagre
    1.62
     milf
    1.61
     hairc
    1.61
     unwarran
    1.61
    Activations Density 0.284%

    No Known Activations