© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2706
    Prev
    Next
    INDEX
    Explanations

    word pairings associated with authorized dealerships and services

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    1757
    +0.10
    0.3%
    370
    +0.08
    0.3%
    67
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    225
    +0.10
    0.03
    1165
    +0.08
    0.03
    37
    +0.08
    0.03
    Negative Logits
    íncia
    -0.72
    mtrl
    -0.72
    ret
    -0.72
    ://
    -0.70
    膜
    -0.70
    struct
    -0.69
    def
    -0.69
    丸
    -0.68
    const
    -0.68
     colspan
    -0.68
    POSITIVE LOGITS
     Authorized
    2.54
     authorized
    2.52
     authorised
    2.31
     maneu
    2.23
     reluct
    2.21
     affor
    2.14
     authorize
    2.13
     authorizing
    2.12
     authorization
    2.12
    authorized
    2.08
    Activations Density 0.178%

    No Known Activations