© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 15158
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal stories and experiences in a military context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    184
    +0.20
    0.7%
    1978
    +0.14
    0.4%
    1013
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.20
    0.04
    1533
    +0.14
    0.02
    1129
    +0.13
    0.05
    Negative Logits
     vogli
    -1.12
     lidl
    -1.08
     vito
    -1.06
     michelin
    -1.05
     bandung
    -1.04
     allarg
    -1.03
     haup
    -1.02
     casio
    -1.02
     peppa
    -1.02
     kosme
    -1.00
    POSITIVE LOGITS
     [
    0.61
     really
    0.61
     everybody
    0.59
     kind
    0.58
     got
    0.58
     went
    0.58
     my
    0.58
     super
    0.57
     totally
    0.56
     stuff
    0.56
    Activations Density 0.306%

    No Known Activations