© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 14577
    Prev
    Next
    INDEX
    Explanations

    facets related to appointments, especially within a political or organizational context

    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
    410
    +0.13
    0.5%
    893
    +0.10
    0.4%
    239
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.13
    0.02
    1479
    +0.10
    0.01
    1778
    +0.10
    0.02
    Negative Logits
     esigenze
    -0.59
     scoper
    -0.54
     conseguenze
    -0.54
     ragioni
    -0.54
    볍
    -0.48
     richieste
    -0.47
     descu
    -0.47
     regole
    -0.46
    bardziej
    -0.46
    Plas
    -0.45
    POSITIVE LOGITS
     appointment
    1.16
     Appointment
    1.14
     appointments
    1.12
     appointing
    1.07
     APPOINT
    1.05
     appoint
    1.05
     Appointments
    1.03
     appointe
    1.01
     appointed
    0.97
     appoints
    0.95
    Activations Density 0.079%

    No Known Activations