© 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. 14079
    Prev
    Next
    INDEX
    Explanations

    words related to disappointment or disapproval

    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
    1233
    +0.09
    0.3%
    1778
    +0.09
    0.3%
    538
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    630
    +0.09
    0.02
    456
    +0.09
    0.02
    1056
    +0.09
    0.02
    Negative Logits
     attes
    -0.70
     utop
    -0.69
     socie
    -0.66
     emble
    -0.66
     abbra
    -0.66
     lapto
    -0.65
     stoff
    -0.64
     espres
    -0.64
     colombia
    -0.63
     malta
    -0.63
    POSITIVE LOGITS
     disappointment
    0.99
     disappointed
    0.91
     disappointing
    0.82
     disappointments
    0.81
     disappoint
    0.80
    enteuer
    0.61
    ingly
    0.57
     disap
    0.57
    enment
    0.52
     dismay
    0.50
    Activations Density 0.083%

    No Known Activations