© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 11134
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns and verbs indicating personal experiences and actions

    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
    1919
    +0.15
    0.5%
    1978
    +0.09
    0.3%
    478
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.15
    0.08
    1415
    +0.09
    0.04
    122
    +0.09
    0.02
    Negative Logits
     poliester
    -0.94
     franz
    -0.84
     cioc
    -0.82
     frambo
    -0.80
     torba
    -0.80
     fré
    -0.80
     ciment
    -0.80
     vost
    -0.80
     monaster
    -0.79
     elef
    -0.79
    POSITIVE LOGITS
     couldn
    0.67
     cannot
    0.65
     wanted
    0.64
     knew
    0.63
     didn
    0.63
     lacked
    0.60
     want
    0.59
     already
    0.59
     didnt
    0.58
     hadn
    0.58
    Activations Density 0.227%

    No Known Activations