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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 854
    Prev
    Next
    INDEX
    Explanations

    information related to specific products or services offered by a company

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    478
    +0.14
    0.6%
    892
    +0.12
    0.5%
    553
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    208
    +0.14
    0.03
    892
    +0.12
    0.02
    651
    +0.11
    0.02
    Negative Logits
    <bos>
    -1.45
     makro
    -1.03
     solidar
    -1.01
     notor
    -0.93
     dras
    -0.89
     katal
    -0.89
     hek
    -0.86
     protes
    -0.86
     erd
    -0.82
    @[+][
    -0.82
    POSITIVE LOGITS
     disagre
    1.48
     impra
    1.47
     unwarran
    1.47
     unlaw
    1.45
     ecru
    1.44
     reluct
    1.40
     affor
    1.38
     tolerably
    1.36
     indescri
    1.36
     Shakspeare
    1.35
    Activations Density 0.061%

    No Known Activations