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. 14016
    Prev
    Next
    INDEX
    Explanations

    photography-related words and concepts

    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
    789
    +0.15
    0.6%
    1325
    +0.12
    0.4%
    1872
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1018
    +0.15
    0.03
    789
    +0.12
    0.03
    1872
    +0.12
    0.02
    Negative Logits
    Iné
    -0.71
    calciatore
    -0.60
     télévis
    -0.60
    geslacht
    -0.60
    DockStyle
    -0.58
    Hentet
    -0.58
    Pozri
    -0.57
    Externé
    -0.56
     Gouver
    -0.55
     Asien
    -0.55
    POSITIVE LOGITS
     photograph
    1.09
     photography
    1.08
     photographs
    1.04
     Photography
    1.00
     photographer
    0.98
     photographing
    0.98
     photographers
    0.97
     photographed
    0.96
     Photograph
    0.92
     Photographs
    0.92
    Activations Density 0.057%

    No Known Activations