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

    Neuronpedia

    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. 4208
    Prev
    Next
    INDEX
    Explanations

    terms related to tax, bills, and fiscal responsibility

    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
    604
    +0.17
    0.5%
    964
    +0.13
    0.4%
    1129
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1851
    +0.17
    0.05
    1948
    +0.13
    0.07
    2025
    +0.09
    0.07
    Negative Logits
    <bos>
    -1.39
     milf
    -1.31
     snoopy
    -1.25
     hentai
    -1.24
     disagre
    -1.18
     intersper
    -1.16
     apprehen
    -1.14
     increa
    -1.14
     yoda
    -1.13
     shenan
    -1.13
    POSITIVE LOGITS
    ActionCreators
    0.60
    Río
    0.54
    loài
    0.53
     ***!
    0.53
     يتيمه
    0.52
    RequiresApi
    0.52
    bloomberg
    0.52
    Londres
    0.52
     legislat
    0.51
     ideolog
    0.51
    Activations Density 1.470%

    No Known Activations