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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 337
    Prev
    Next
    INDEX
    Explanations

    legal clauses and terms related to financial documents

    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
    50
    +0.10
    0.4%
    411
    +0.08
    0.4%
    1047
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    411
    +0.10
    0.03
    1149
    +0.08
    0.03
    461
    +0.07
    0.03
    Negative Logits
    <bos>
    -1.30
    public
    -0.84
    ,
    -0.82
    .
    -0.81
        
    -0.79
     in
    -0.79
     on
    -0.76
            
    -0.76
    -0.75
     and
    -0.74
    POSITIVE LOGITS
     affor
    2.38
     stockholm
    2.33
     lidl
    2.32
     maneu
    2.32
     embodi
    2.15
     eiffel
    2.12
     scrat
    2.11
     volunte
    2.11
     shenan
    2.11
     michelin
    2.10
    Activations Density 0.105%
    No Known Activations