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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13317
    Prev
    Next
    INDEX
    Explanations

    adjectives describing differences and contrasts between things or situations

    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
    394
    +0.13
    0.4%
    856
    +0.13
    0.4%
    453
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    605
    +0.13
    0.00
    630
    +0.13
    0.02
    2044
    +0.11
    0.05
    Negative Logits
     snoopy
    -0.99
     reluct
    -0.98
     gaily
    -0.96
     inev
    -0.94
     depic
    -0.94
     strick
    -0.94
     vainly
    -0.93
     apprehen
    -0.92
     impra
    -0.92
     disagre
    -0.92
    POSITIVE LOGITS
    .
    0.81
    <bos>
    0.68
    stdarg
    0.55
    。
    0.53
    。「
    0.51
    —
    0.49
    GOTREF
    0.49
     AssemblyCulture
    0.48
     gyhoeddwyd
    0.47
    :
    0.47
    Activations Density 0.416%

    No Known Activations