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. 5287
    Prev
    Next
    INDEX
    Explanations

    keywords related to customs, taxes, and fees

    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
    411
    +0.15
    0.8%
    871
    +0.12
    0.6%
    241
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.15
    0.03
    411
    +0.12
    0.02
    144
    +0.12
    0.03
    Negative Logits
    <bos>
    -1.59
     Bolt
    -0.58
     Dek
    -0.57
    Bol
    -0.56
    bol
    -0.55
    Dek
    -0.55
    bolt
    -0.54
     Bol
    -0.54
    card
    -0.54
    BOL
    -0.52
    POSITIVE LOGITS
     duty
    1.34
     Duty
    1.32
    duty
    1.28
    Duty
    1.25
     DUTY
    1.22
     duties
    1.09
     Duties
    1.01
    Duties
    0.84
    DUT
    0.77
     plagio
    0.76
    Activations Density 0.387%

    No Known Activations