© 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. 6433
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology issues and software activations

    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
    1013
    +0.12
    0.3%
    1857
    +0.08
    0.2%
    1614
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1579
    +0.12
    0.04
    1055
    +0.08
    0.05
    1592
    +0.08
    0.04
    Negative Logits
     ?...
    -1.28
     emphat
    -1.27
     suscep
    -1.15
     !...
    -1.11
    :,,
    -1.10
     increa
    -1.06
     effe
    -1.05
     inext
    -1.04
     aen
    -1.03
     alre
    -1.01
    POSITIVE LOGITS
     except
    1.00
     whatsoever
    0.93
    except
    0.88
     until
    0.83
     unless
    0.81
     nor
    0.77
    Except
    0.74
     Except
    0.71
    until
    0.70
     anymore
    0.68
    Activations Density 0.447%

    No Known Activations