© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 1072
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial analysis and comparison

    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
    964
    +0.24
    0.8%
    227
    +0.21
    0.7%
    1177
    +0.17
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.24
    0.13
    964
    +0.21
    0.09
    50
    +0.17
    0.10
    Negative Logits
    OGND
    -0.88
     Walkover
    -0.87
     '\\;'
    -0.86
    <bos>
    -0.86
     nakalista
    -0.83
     poveznice
    -0.83
     Paglinawan
    -0.82
     noten
    -0.80
     gela
    -0.80
     AssemblyCulture
    -0.80
    POSITIVE LOGITS
     impra
    2.09
     disagre
    2.02
     shenan
    2.02
     maneu
    1.99
     apprehen
    1.97
     unspeak
    1.97
     uninten
    1.94
     reluct
    1.93
     depic
    1.92
     increa
    1.90
    Activations Density 1.496%

    No Known Activations