© 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. 13302
    Prev
    Next
    INDEX
    Explanations

    mention of the word "jail" or related terms

    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
    1937
    +0.13
    0.4%
    421
    +0.12
    0.4%
    920
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1691
    +0.13
    0.02
    920
    +0.12
    0.02
    1937
    +0.12
    0.02
    Negative Logits
     underval
    -0.49
    Sif
    -0.47
     intersper
    -0.47
    Ked
    -0.45
    Gele
    -0.44
     verst
    -0.44
     Burke
    -0.43
    ANP
    -0.43
     endow
    -0.43
     vā
    -0.42
    POSITIVE LOGITS
     jail
    1.12
    Jail
    1.06
     Jail
    1.05
    jail
    0.96
     jails
    0.94
     jailed
    0.81
     prison
    0.66
    Prison
    0.63
     inmates
    0.63
     pecuni
    0.62
    Activations Density 0.043%

    No Known Activations