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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 891
    Prev
    Next
    INDEX
    Explanations

    words related to web browsers and user authentication issues

    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
    1937
    +0.09
    0.3%
    204
    +0.08
    0.3%
    789
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    204
    +0.09
    0.02
    1343
    +0.08
    0.03
    816
    +0.07
    0.02
    Negative Logits
     quitted
    -1.54
     vainly
    -1.52
     apprehen
    -1.43
     intersper
    -1.37
     tolerably
    -1.30
     encomp
    -1.28
     gaily
    -1.27
     impelled
    -1.25
     ineffec
    -1.24
     reluct
    -1.22
    POSITIVE LOGITS
     brow
    1.74
     lip
    1.61
     Brow
    1.35
     eyebrow
    1.31
    Brow
    1.28
     Lip
    1.26
    Lip
    1.25
     brows
    1.19
     eyebrows
    1.18
     tongue
    1.16
    Activations Density 0.197%

    No Known Activations