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-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 149
    Prev
    Next
    INDEX
    Explanations

    mentions of cryptocurrencies, particularly Bitcoin, its market dominance, fluctuations, and regulatory actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1356
    +0.12
    0.4%
    1445
    +0.09
    0.3%
    20
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    20
    +0.12
    0.05
    230
    +0.09
    0.04
    1746
    +0.08
    0.03
    Negative Logits
     ejus
    -0.61
     maksi
    -0.58
     Minangkabau
    -0.53
     quæ
    -0.52
    ghijkl
    -0.50
    @[+][
    -0.50
     potest
    -0.50
    <bos>
    -0.48
     Tangerang
    -0.48
    contentLoaded
    -0.48
    POSITIVE LOGITS
     cryptocurrency
    0.53
     currencies
    0.45
     Cryptocurrency
    0.45
     monetary
    0.42
     hashlib
    0.42
     liquidity
    0.42
     hype
    0.42
     billions
    0.41
     Bitcoin
    0.40
     currency
    0.40
    Activations Density 0.473%

    No Known Activations