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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 14481
    Prev
    Next
    INDEX
    Explanations

    mentions of music albums, artists, and EPs

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.18
    0.6%
    486
    +0.09
    0.3%
    1150
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    872
    +0.18
    0.06
    458
    +0.09
    0.04
    678
    +0.08
    0.05
    Negative Logits
    <bos>
    -3.24
    Autoritní
    -0.90
    PerformLayout
    -0.83
    IsContent
    -0.82
     sumpay
    -0.78
    Δείτε
    -0.78
    HasColumnType
    -0.77
    migrationBuilder
    -0.77
    Пусть
    -0.76
    ⓧ
    -0.75
    POSITIVE LOGITS
     affor
    2.39
     impra
    2.39
     increa
    2.32
     reluct
    2.31
     disagre
    2.30
     maneu
    2.29
     volunte
    2.17
     unspeak
    2.17
     inev
    2.11
     apprehen
    2.11
    Activations Density 0.537%

    No Known Activations