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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2333
    Prev
    Next
    INDEX
    Explanations

    personal account narratives with multiple instances of 'I'

    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
    381
    +0.22
    0.8%
    1919
    +0.17
    0.6%
    805
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.22
    0.12
    805
    +0.17
    0.09
    1415
    +0.14
    0.06
    Negative Logits
     affez
    -1.33
     susun
    -1.25
     poft
    -1.22
     répon
    -1.17
     parlamento
    -1.13
     LIRE
    -1.10
     venuto
    -1.07
     hcm
    -1.06
     sapat
    -1.05
     parati
    -1.04
    POSITIVE LOGITS
     knew
    0.89
    <_>
    0.86
     didn
    0.85
     went
    0.83
     had
    0.81
     I
    0.80
     got
    0.80
     couldn
    0.79
     did
    0.78
     realized
    0.76
    Activations Density 0.280%

    No Known Activations