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. 13526
    Prev
    Next
    INDEX
    Explanations

    phrases related to criticizing or expressing disappointment

    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
    1823
    +0.10
    0.3%
    872
    +0.08
    0.2%
    1935
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1823
    +0.10
    0.03
    1890
    +0.08
    0.04
    1543
    +0.07
    0.03
    Negative Logits
     philanth
    -1.11
     fortn
    -1.08
     encomp
    -1.07
     shenan
    -1.05
     Immig
    -1.05
     volunte
    -1.04
     impractica
    -1.02
     resear
    -1.01
     reluct
    -1.00
     increa
    -0.99
    POSITIVE LOGITS
     original
    0.76
    original
    0.75
    Original
    0.72
    <bos>
    0.69
     Original
    0.67
     originales
    0.65
     ORIGINAL
    0.62
     basics
    0.62
    integrity
    0.61
     gainera
    0.61
    Activations Density 0.430%

    No Known Activations