© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2184
    Prev
    Next
    INDEX
    Explanations

    references to resource allocation in various contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1520
    +0.08
    0.3%
    1872
    +0.08
    0.2%
    172
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.08
    0.02
    1872
    +0.08
    0.02
    450
    +0.08
    0.01
    Negative Logits
    ⓧ
    -0.52
    /**
    -0.50
     slide
    -0.50
    <?
    -0.49
     съдържа
    -0.49
    cloud
    -0.47
    <!--
    -0.47
    辞
    -0.46
     cloud
    -0.46
     Gene
    -0.46
    POSITIVE LOGITS
     allocation
    2.69
     allocations
    2.60
     Allocation
    2.53
     Alloc
    2.44
     allocated
    2.34
     allocate
    2.23
     allocating
    2.19
    allocation
    2.14
     alloc
    2.10
    Allocation
    2.10
    Activations Density 0.197%

    No Known Activations