© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 547
    Prev
    Next
    INDEX
    Explanations

    mentions of horse racing events or related terms, particularly focusing on specific races like the Derby

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    204
    +0.10
    0.3%
    1472
    +0.10
    0.3%
    2011
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.10
    0.06
    1120
    +0.10
    0.05
    1343
    +0.10
    0.05
    Negative Logits
    <tfoot>
    -0.69
    mainAxisSize
    -0.64
    imanapun
    -0.64
     săptăm
    -0.59
    bootstrapcdn
    -0.59
    TagMode
    -0.57
    templateUrl
    -0.57
    ={({
    -0.57
    modelBuilder
    -0.57
     hjæl
    -0.57
    POSITIVE LOGITS
     Derby
    1.40
    Derby
    1.30
     Juf
    1.20
     ftu
    1.10
     Confu
    1.04
     fays
    1.01
     vns
    1.01
     fta
    1.01
     depic
    0.98
     emphat
    0.98
    Activations Density 0.315%

    No Known Activations