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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5700
    Prev
    Next
    INDEX
    Explanations

    instances of the word "tin" or related terms

    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
    1323
    +0.20
    1.0%
    1047
    +0.16
    0.9%
    1023
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.20
    0.04
    1323
    +0.16
    0.04
    1343
    +0.14
    0.06
    Negative Logits
    <bos>
    -0.71
    Cartney
    -0.57
    <?
    -0.52
    paddingVertical
    -0.51
    FlatStyle
    -0.51
     święta
    -0.50
     DCP
    -0.49
    ticello
    -0.47
    PostMapping
    -0.47
     Bulgaria
    -0.47
    POSITIVE LOGITS
     Tin
    1.14
    Tin
    1.13
     tin
    1.10
     Sn
    1.06
    Sn
    0.99
     TIN
    0.82
     sn
    0.80
     tins
    0.80
    tin
    0.77
    TIN
    0.74
    Activations Density 0.592%

    No Known Activations