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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 297
    Prev
    Next
    INDEX
    Explanations

    references to financial aspects, such as fortune or income, specifically emphasizing negative instances like errors

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    783
    +0.11
    0.3%
    25
    +0.09
    0.3%
    1937
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    195
    +0.11
    0.02
    783
    +0.09
    0.02
    1935
    +0.09
    0.02
    Negative Logits
    <bos>
    -0.61
     архивлан
    -0.56
    دانشنامهٔ
    -0.52
     geha
    -0.51
    queryInterface
    -0.50
     hã
    -0.50
     виді
    -0.50
    richTextPanel
    -0.50
     защото
    -0.49
    afterEach
    -0.49
    POSITIVE LOGITS
     fortune
    2.79
     Fortune
    2.71
    Fortune
    2.39
    fortune
    2.23
     fortunes
    2.08
    fortunes
    1.76
     fortuna
    1.38
     FORT
    1.30
     stockholm
    1.16
     fortun
    1.15
    Activations Density 0.200%

    No Known Activations