Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 1777
    Prev
    Next
    INDEX
    Explanations

    inaccuracies or negative emotions in a passage

    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
    2015
    +0.14
    0.4%
    1871
    +0.13
    0.4%
    906
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1291
    +0.14
    0.06
    872
    +0.13
    0.07
    2015
    +0.12
    -0.01
    Negative Logits
     kask
    -0.94
     silikon
    -0.93
     mikrofon
    -0.92
     plak
    -0.90
     koron
    -0.89
     karton
    -0.86
     alkoh
    -0.85
     traktor
    -0.83
     moza
    -0.83
     foton
    -0.80
    POSITIVE LOGITS
    municipi
    0.88
     psycopg
    0.87
    <bos>
    0.84
     uchiha
    0.83
     pymysql
    0.82
     îna
    0.82
     milf
    0.78
     smtplib
    0.77
     sasuke
    0.76
    yaitu
    0.76
    Activations Density 0.911%

    No Known Activations