© 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. 4148
    Prev
    Next
    INDEX
    Explanations

    phrases related to warnings, threats, or potential consequences

    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
    1438
    +0.13
    0.4%
    404
    +0.13
    0.4%
    1265
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    404
    +0.13
    0.06
    1406
    +0.13
    0.04
    757
    +0.12
    0.04
    Negative Logits
     pymysql
    -0.90
     smtplib
    -0.83
     psycopg
    -0.80
     pymongo
    -0.66
     heapq
    -0.64
     hashlib
    -0.60
     pylab
    -0.58
     functools
    -0.55
     tempfile
    -0.53
    ghijklmnop
    -0.52
    POSITIVE LOGITS
     if
    0.71
     Souha
    0.70
     Mère
    0.70
     mahd
    0.67
     quoique
    0.63
     IF
    0.59
     Infir
    0.59
     Quoi
    0.58
     Messieurs
    0.58
     they
    0.57
    Activations Density 0.133%

    No Known Activations