© 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. 13688
    Prev
    Next
    INDEX
    Explanations

    the word 'possibility' or phrases related to considerations and evaluations of potential circumstances

    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
    869
    +0.15
    0.5%
    871
    +0.12
    0.4%
    168
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    869
    +0.15
    0.03
    2030
    +0.12
    0.02
    871
    +0.11
    0.02
    Negative Logits
     guardare
    -0.56
     dimenti
    -0.55
    Perché
    -0.54
     migli
    -0.53
     Più
    -0.52
     avete
    -0.52
    Vedi
    -0.51
    Più
    -0.51
     Perché
    -0.51
     gius
    -0.49
    POSITIVE LOGITS
    possibility
    0.95
     Possibility
    0.94
     possibility
    0.92
    Possibility
    0.78
     Possibilities
    0.73
     possib
    0.69
     possibilities
    0.68
     posibilidad
    0.68
     pylab
    0.67
     fays
    0.60
    Activations Density 0.062%

    No Known Activations