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. 1318
    Prev
    Next
    INDEX
    Explanations

    information related to duration or passage of time

    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
    889
    +0.14
    0.5%
    297
    +0.12
    0.4%
    1013
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1830
    +0.14
    0.06
    297
    +0.12
    0.07
    1856
    +0.12
    0.07
    Negative Logits
    Δια
    -0.69
    asteroide
    -0.69
     Walkover
    -0.68
    Selección
    -0.67
     impon
    -0.67
     Diciembre
    -0.67
    endpush
    -0.66
     dezembro
    -0.65
     novembro
    -0.64
     outubro
    -0.64
    POSITIVE LOGITS
     unspeak
    1.23
     sophistic
    1.21
     disagre
    1.20
     unwarran
    1.18
     maneu
    1.17
     impra
    1.16
     gaily
    1.14
     affor
    1.12
     pamph
    1.11
     excru
    1.10
    Activations Density 0.170%

    No Known Activations