Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 14833
    Prev
    Next
    INDEX
    Explanations

    words related to specific characters or 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
    553
    +0.17
    0.7%
    1708
    +0.12
    0.5%
    1328
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    553
    +0.17
    0.03
    1437
    +0.12
    0.02
    1708
    +0.11
    0.02
    Negative Logits
     Collins
    -0.48
     Steffen
    -0.47
    érard
    -0.46
    XmlAccessorType
    -0.43
     Bays
    -0.43
    Collins
    -0.43
    нодоро
    -0.43
     Bernhard
    -0.42
     Catan
    -0.42
     Valky
    -0.41
    POSITIVE LOGITS
     Gro
    1.14
     GRO
    1.13
    Gro
    1.03
     gro
    1.01
    gro
    0.92
     gr
    0.92
    GRO
    0.92
     Gr
    0.85
    Gr
    0.83
    gr
    0.78
    Activations Density 0.122%

    No Known Activations