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. 308
    Prev
    Next
    INDEX
    Explanations

    words related to criticism and disagreement

    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
    1363
    +0.15
    0.6%
    122
    +0.14
    0.5%
    1272
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.15
    0.04
    1272
    +0.14
    0.04
    122
    +0.13
    0.03
    Negative Logits
    OGND
    -0.63
    Hvor
    -0.48
     koš
    -0.47
    hasMoreElements
    -0.43
    centerTitle
    -0.43
    Hozzáférés
    -0.43
    amssymb
    -0.42
    jTextField
    -0.40
    ENOMEM
    -0.40
     StringTokenizer
    -0.40
    POSITIVE LOGITS
     bl
    1.00
     Bl
    0.99
     BL
    0.99
     Bla
    0.95
    Bl
    0.91
    Bla
    0.90
     bla
    0.89
    BL
    0.89
     BLA
    0.88
    bl
    0.88
    Activations Density 0.148%

    No Known Activations