© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2014
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    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
    +0.09
    0.3%
    1103
    +0.06
    0.2%
    421
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.09
    0.04
    344
    +0.06
    0.02
    1614
    +0.05
    0.03
    Negative Logits
    <bos>
    -1.31
     plundered
    -0.73
     overthrown
    -0.70
     endeavored
    -0.69
    
    -0.66
     enshr
    -0.66
     endow
    -0.65
     inaugurate
    -0.65
     banish
    -0.64
     abolish
    -0.64
    POSITIVE LOGITS
     dises
    1.21
     aen
    1.20
     nomine
    1.17
     grati
    1.15
     cæ
    1.14
     applau
    1.13
     magis
    1.13
     tamen
    1.12
     hcm
    1.09
     nece
    1.08
    Activations Density 0.289%

    No Known Activations