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. 377
    Prev
    Next
    INDEX
    Explanations

    real estate property details

    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
    453
    +0.15
    0.4%
    1042
    +0.13
    0.4%
    906
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    906
    +0.15
    0.00
    2037
    +0.13
    0.03
    453
    +0.10
    0.03
    Negative Logits
     shenan
    -2.11
     reluct
    -2.03
     pamph
    -2.00
     apprehen
    -1.93
     disagre
    -1.90
     unspeak
    -1.82
     gaily
    -1.81
     philanth
    -1.78
     intersper
    -1.77
     maneu
    -1.74
    POSITIVE LOGITS
     Walkover
    0.95
     lenker
    0.88
    SourceChecksum
    0.87
    Datuak
    0.78
    WindowConstants
    0.77
     CURLOPT
    0.76
     Mérimée
    0.75
     Affiliations
    0.73
     SEDS
    0.73
     Fichier
    0.72
    Activations Density 0.130%

    No Known Activations