© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 965
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions indicating hypothetical scenarios

    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
    1978
    +0.11
    0.3%
    674
    +0.10
    0.3%
    1581
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1811
    +0.11
    0.04
    1299
    +0.10
    0.02
    1776
    +0.10
    0.03
    Negative Logits
    Ekster
    -0.53
    bff
    -0.52
     actionTypes
    -0.51
     Also
    -0.48
    Véxase
    -0.48
     psycopg
    -0.48
     accordingly
    -0.47
     pylab
    -0.46
     Surprisingly
    -0.46
     Accordingly
    -0.46
    POSITIVE LOGITS
     affez
    0.85
     venuto
    0.84
     mosso
    0.76
     quoc
    0.75
     LIRE
    0.73
     tranquillo
    0.72
     susun
    0.72
     bawat
    0.71
     bahay
    0.70
     jaya
    0.70
    Activations Density 0.375%

    No Known Activations