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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 188
    Prev
    Next
    INDEX
    Explanations

    technical specifications related to electronic devices, specifically focusing on stereo-related features

    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
    1065
    +0.11
    0.3%
    1548
    +0.10
    0.3%
    1861
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.11
    0.03
    1065
    +0.10
    0.02
    1896
    +0.09
    0.01
    Negative Logits
    GIH
    -0.64
    cshtml
    -0.63
    ObjectModel
    -0.63
    SourceChecksum
    -0.61
    LogFactory
    -0.60
    cloudflare
    -0.59
    SPJ
    -0.58
    onAttach
    -0.57
    AtIndexPath
    -0.57
    LoggerFactory
    -0.57
    POSITIVE LOGITS
     stere
    2.61
     stereo
    2.46
     Stere
    2.42
     Stereo
    2.29
    stereo
    2.20
    Stere
    2.18
    Stereo
    2.12
     stereotype
    1.81
    stere
    1.77
     stereotyp
    1.73
    Activations Density 0.235%

    No Known Activations