Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 7941
    Prev
    Next
    INDEX
    Explanations

    words related to hesitation or reluctance

    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
    +0.13
    0.4%
    1921
    +0.11
    0.3%
    663
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    630
    +0.13
    0.03
    1921
    +0.11
    0.03
    1960
    +0.10
    0.03
    Negative Logits
     lele
    -1.35
     fta
    -1.25
     mef
    -1.25
     Simult
    -1.22
     aen
    -1.21
     Cfr
    -1.21
     simplif
    -1.21
     Juf
    -1.19
     endom
    -1.19
     dora
    -1.19
    POSITIVE LOGITS
     hesitate
    0.84
     hesitant
    0.82
     reluctant
    0.80
     hesitation
    0.78
     shy
    0.76
     afraid
    0.72
     reluctance
    0.65
     hesitated
    0.65
     about
    0.63
    于
    0.59
    Activations Density 0.156%

    No Known Activations