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. 15033
    Prev
    Next
    INDEX
    Explanations

    words related to financial transactions and services

    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
    +0.31
    1.5%
    1842
    +0.12
    0.6%
    1870
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.31
    0.22
    1870
    +0.12
    0.09
    908
    +0.11
    0.11
    Negative Logits
    <bos>
    -2.72
     intersper
    -1.22
     encomp
    -1.12
     unve
    -1.04
     disbur
    -1.01
     tranf
    -0.98
     endow
    -0.97
     depic
    -0.97
     shenan
    -0.96
     quitted
    -0.95
    POSITIVE LOGITS
     OrderedDict
    0.58
    numericUpDown
    0.56
    󠁢
    0.55
     AssertionError
    0.51
    hWnd
    0.51
    tabControl
    0.50
     faca
    0.50
     smtplib
    0.49
    TypedValue
    0.48
     cooperativa
    0.48
    Activations Density 4.364%

    No Known Activations