© 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. 13860
    Prev
    Next
    INDEX
    Explanations

    single words ending in 'ed'

    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
    1350
    +0.11
    0.3%
    690
    +0.11
    0.3%
    1379
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1350
    +0.11
    0.06
    569
    +0.11
    0.06
    690
    +0.10
    0.04
    Negative Logits
     makro
    -0.85
     kriminal
    -0.77
     kosme
    -0.77
     traktor
    -0.76
     antik
    -0.74
     kaos
    -0.73
     Nö
    -0.73
     Strukt
    -0.72
     Kombin
    -0.72
     kase
    -0.71
    POSITIVE LOGITS
    relenting
    0.87
    solicited
    0.83
    wavering
    0.82
     nahilalakip
    0.72
    sightly
    0.69
    thinkable
    0.69
     hornblende
    0.68
    compromising
    0.66
     tramonto
    0.65
    mistak
    0.63
    Activations Density 0.294%

    No Known Activations