© 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. 14649
    Prev
    Next
    INDEX
    Explanations

    phrases related to analysis and prediction

    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
    752
    +0.09
    0.3%
    1288
    +0.08
    0.2%
    1253
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    62
    +0.09
    0.05
    100
    +0.08
    0.04
    1265
    +0.08
    0.04
    Negative Logits
     accla
    -1.49
     reluct
    -1.37
     shenan
    -1.29
     disagre
    -1.28
     affor
    -1.27
     embra
    -1.25
     Souha
    -1.24
     inconce
    -1.23
     encomp
    -1.21
     philanth
    -1.21
    POSITIVE LOGITS
     any
    0.77
     there
    0.72
     anything
    0.70
     finding
    0.65
    any
    0.63
     unless
    0.63
    cautions
    0.61
     ANY
    0.60
    there
    0.60
     many
    0.59
    Activations Density 0.416%

    No Known Activations