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. 14012
    Prev
    Next
    INDEX
    Explanations

    names of individuals and locations

    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
    50
    +0.17
    0.6%
    752
    +0.14
    0.4%
    1445
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    129
    +0.17
    0.04
    16
    +0.14
    0.07
    50
    +0.14
    0.05
    Negative Logits
    <bos>
    -0.80
     SPECIFICATION
    -0.68
     SAMPLING
    -0.68
     POLLUTION
    -0.67
     FACILITY
    -0.66
    VISIONS
    -0.66
     ALUMIN
    -0.64
     apartament
    -0.63
     CAPACITY
    -0.62
     bituminous
    -0.62
    POSITIVE LOGITS
     Sén
    1.39
     Docteur
    1.33
     Souha
    1.33
     Traité
    1.20
     Că
    1.18
     Membre
    1.17
     Meilleur
    1.16
     Châ
    1.16
     Venise
    1.15
     Chapitre
    1.13
    Activations Density 0.386%

    No Known Activations