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. 5321
    Prev
    Next
    INDEX
    Explanations

    keywords related to office equipment or tasks

    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
    50
    +0.14
    0.6%
    783
    +0.12
    0.5%
    1896
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    783
    +0.14
    0.10
    1385
    +0.12
    0.11
    1971
    +0.12
    0.07
    Negative Logits
    <bos>
    -1.49
    HasColumnType
    -0.89
    पया
    -0.81
     AssemblyCompany
    -0.80
    WithMany
    -0.76
     مرئيه
    -0.76
    IsRequired
    -0.75
    WriteBarrier
    -0.74
    RectangleBorder
    -0.72
    GeneratedMessage
    -0.72
    POSITIVE LOGITS
     disagre
    2.07
     apprehen
    2.03
     increa
    1.99
     unspeak
    1.99
     reluct
    1.98
     gaily
    1.95
     maneu
    1.95
     suscep
    1.93
     unwarran
    1.93
     tolerably
    1.91
    Activations Density 1.076%

    No Known Activations