© 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. 12157
    Prev
    Next
    INDEX
    Explanations

    references to abilities or skills

    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
    1806
    +0.14
    0.4%
    1256
    +0.11
    0.4%
    1839
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1806
    +0.14
    0.04
    1256
    +0.11
    0.03
    869
    +0.10
    0.03
    Negative Logits
     indestru
    -1.28
     embra
    -1.24
     suspic
    -1.24
     inconce
    -1.23
     emphat
    -1.23
     disgra
    -1.19
     benevol
    -1.19
     Juf
    -1.16
     indoc
    -1.16
     ingrat
    -1.14
    POSITIVE LOGITS
     ability
    1.12
     Ability
    1.08
    Ability
    1.04
     abilities
    0.96
    ability
    0.88
     able
    0.86
     capability
    0.76
     Abilities
    0.75
     Able
    0.74
    ABILITY
    0.72
    Activations Density 0.056%

    No Known Activations