© 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. 11891
    Prev
    Next
    INDEX
    Explanations

    statements relating to help or assistance

    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
    1222
    +0.13
    0.5%
    61
    +0.11
    0.4%
    1271
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1222
    +0.13
    0.05
    240
    +0.11
    0.04
    61
    +0.10
    0.04
    Negative Logits
     maî
    -0.51
     getNome
    -0.51
     orific
    -0.48
     bisous
    -0.48
     conç
    -0.48
     évit
    -0.47
    Gis
    -0.47
     xxl
    -0.47
     mérit
    -0.45
    lihatkan
    -0.45
    POSITIVE LOGITS
     help
    0.94
     helping
    0.80
    help
    0.80
     ļ
    0.77
     helped
    0.76
     Help
    0.74
     helps
    0.74
    helped
    0.74
     HELP
    0.74
     nepiecieš
    0.70
    Activations Density 0.080%

    No Known Activations